Tool search 164,478 tools · 10,067 live servers

Retrieves the interactions between the query proteins. Use this method only when you specifically need to list the interactions between all proteins in your query set. If user asks for 'physical' or 'complex' use 'physical' network type. - For a **single protein**, the network includes that protein and its top 10 most likely interaction partners, plus all interactions among those partners. - For **multiple proteins**, the network includes all direct interactions between them. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". - STRING does not store or report information about self-interactions/homomers; if asked, explain the limitation. If few or no interactions are returned, consider reducing the `required_score`. For large query sets (>50 proteins), consider increasing the `required_score` (e.g. ≥700) to focus on high-confidence interactions and avoid overly dense networks. - Expand the names of score sources: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text-mining)

Retrieves all interaction partners for one or more proteins from STRING. This tool returns all known interactions between your query protein(s) and **any other proteins in the STRING database**. - Use this when asking **“What does TP53 interact with?”** - It differs from the `network` tool, which only shows interactions **within the input set** or a limited extension of it. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". You can filter for strong interactions using `required_score`. - Evidence scores: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text mining)

Creates a downloadable file for STRING-derived results. Use this tool when the user explicitly asks to download, save, export, or receive a file containing STRING data, tables, protein lists, enrichment results, networks, etc. When a response would otherwise include a publication-style or supplementary result table, or another table clearly intended for reuse outside chat, mention that a downloadable TSV/CSV file can be generated on request. Ask whether they want the file, unless they already requested it. Do not create the file until the user asks for it. Do not store unrelated data or full conversation transcripts.

Write a text file into a persistent Linux machine. Use this instead of shelling out with cat/echo — no quoting to get wrong.

Read a text file out of a persistent Linux machine.

Stop a persistent Linux machine. The disk and the network address are kept, so starting it again returns the same files at the same address. Stop machines you are done with — a stopped machine costs only its disk.

Permanently delete a persistent Linux machine AND its disk. This cannot be undone — use scalix_computer_stop if you may want the files back.

Create a new container image build from a Git repository or Dockerfile.

Deploy a v2 app: an HTML document plus a capability manifest, hosted at its own URL. A redeploy only needs the content that changed. Every content field is optional when `app_id` is given, and an omitted one keeps what is live: omit `manifest` for an HTML-only change, omit `html` for a manifest-only change, omit `assets` to keep the current files. This is the cheap path and the default, because an omitted field costs no output tokens at all: a one-line colour change does not resend the whole document, and a manifest edit does not resend it either. A field only needs sending when its content differs from what is live. `assets: []` is the explicit way to clear the asset set, and omitting all three is refused, since there would be nothing to change. The extension keys used most often: app metadata; collections, with per-collection write, update, read and delete role lists, where write gates creates and also gates updates unless an update list is declared; externalHosts, a fetch allowlist; cdn, to allow CDN scripts and styles; capabilities, for Permissions-Policy opt-ins; embeds, an iframe frame-src allowlist; notify, for email-on-row rules; webhooks, for signed HTTP POST on-row rules; and agentTasks, to queue work for an agent running on the owner's own machine, described as a prompt rather than as code. The manifest grammar is documented in the Homespun guide that get_skill returns. Pass no `app_id` to create, which mints a slug and URL and requires both `html` and `manifest`, or pass `app_id` to redeploy an existing app. Supply the HTML inline as `html`, or as `html_path`, an absolute path read on the MCP-server host, which is the relay for a hosted connector or the CLI host for a locally-run one, and not the remote agent's machine; it avoids retransmitting a large HTML file on every deploy, only a locally-run connector can read it, and inline `html` wins if both are given. `dry_run:true` (alias `check`) validates only: it runs the full manifest and asset validation, the redeploy compat gate and the schedule-timezone advisory, then returns { ok, warnings, compat?, breaks? } without creating a version or mutating anything, and it resolves omitted fields the same way a real deploy would, so it reports on exactly the deploy that would run. A redeploy is refused with manifest_incompatible_redeploy, unless force:true, when it would strand rows already written (dropping a collection, tightening a schema, flipping appendOnly), or when it would widen what the app's install screen discloses: a collection's read reaching further than the live manifest, a capability added, cdn turned on, or a host added to externalHosts, embeds or a webhook target. The break quotes the sentence a user would now be asked to approve. Taking access away never prompts: dropping a role, dropping a capability, host or webhook, turning cdn off, or adding update:[\"creator\"] to a write:[\"anyone\"] collection, all redeploy clean. A removed collection is detached rather than deleted. Images, fonts, audio, video and data files ship with the app in the same call via `assets[]`. Each is validated and stored app-scoped and served at its `path` on the app's own origin, so the HTML references it by a stable same-origin path such as `<img src=\"frames/000.jpg\">`; media and font paths support HTTP Range for seeking. A redeploy's assets replace the previous version's set when sent, carry over when omitted, and are cleared by `assets: []`. Returns { app_id, slug, url, version, visibility, created } on create, or { app_id, version, compat, breaks? } on redeploy.

Binary attachments (images, PDFs, audio, video) referenced from event payloads and input_data via `format: homespun-attachment-id`. Actions: upload, fetch, presign, finalize, download, show, list, delete, mint_token, revoke_token, list_tokens. Choosing an upload path matters for cost. An inline upload with `content_base64` carries the bytes in the tool-call arguments, so they enter the model context at a token cost proportional to file size, paid again on every retry; a few-hundred-KB image is already expensive. Two paths avoid that entirely: fetch, when the bytes are reachable at a URL, and presign plus finalize, when the client can PUT the raw bytes out of band. Inline upload suits small assets and clients that have neither a URL nor an out-of-band PUT. fetch takes { source_url (https), scope } and the relay downloads the URL itself behind an SSRF guard (https only, no private, loopback or metadata hosts, DNS pinned, redirects refused, size-capped and timed out), then runs the same byte-sniff, allowlist, size, quota and scan checks as any upload. It works on any storage backend. upload takes either `content_base64` (base64 bytes, no filesystem) or `file_path` (an absolute path read on the relay host, so it only applies when the file is local to the relay). presign plus finalize is token-free: presign with { mime, size, sha256, scope } returns { put_url, attachment_id }, the caller PUTs the raw bytes to put_url over plain HTTP out of band, then finalize with the attachment_id. At finalize the relay re-reads the stored bytes, sniffs the real type, and enforces the same allowlist, size, sha256, quota and scan checks, so a presign that misstates its mime is caught and never served inline. The presigned path requires the Azure storage backend; a filesystem-backed relay returns a clear not-supported error and fetch or inline upload apply there instead. download writes to an absolute out_path or returns base64. An upload is scoped to agent (the default, reusable) or app. mint_token returns a /b/<token> capability URL, shown once, that a browser can GET without the caller's API key.

Reports a problem with homespun itself to the relay operator, and lists what this agent has already reported. A report is the operator's only visibility into a failure that happened inside an agent's session, so an unreported one is a failure nobody can fix. The channel covers homespun's own behaviour: a 5xx, or an error code the guide does not describe; a disagreement between documented and observed behaviour; something the tool surface cannot express, such as a missing capability or a schema that contradicts itself; an app misbehaving in a way that traces back to the platform (the bridge, the runtime, serving, the data API) rather than to authored HTML; or a guide that was wrong, ambiguous or silent. Outside its scope: the human's own task; bugs in an app the agent authored; presentation preferences, which belong in `taste`; the human's own configuration, such as a missing API key or the wrong account; and a 4xx caused by the agent's own arguments, except where the error message itself was misleading, which is a documentation problem best filed as a `note`. Duplicates cost the operator triage rather than adding signal. Action `list` returns this agent's own submissions, newest first, so a failure already recorded needs no second row: one report covers one distinct failure, however many times it was retried. The operator sees the row and not the session, so a bare "deploy failed" is not actionable. An actionable `message` carries the surface (mcp, cli, relay or app-runtime); where it happened (the tool or route); the skill version, from the `<!-- homespun skill vX.Y.Z -->` comment at the top of the guide; what was expected, in one line; what was observed, in one line carrying the exact error code and message; and the minimal steps or arguments that reproduce it. `type` is bug for something broken, feature for something missing, note for a rough edge or a confusing doc. `app_id` scopes a report to one app. There is no reply channel, so a report is not a route to an answer. Actions: create files one report; list returns this agent's own submissions, newest first, paginated by `before`.

Agent identity and binding. Actions: whoami returns the resolved relay URL, the active profile and whether a key is configured, with no network call and no secrets; claim binds this agent to a human using a one-shot claim code from their Settings UI, and is one-way; logout clears the locally saved key and profile but does not revoke it on the relay, which is what the `key` tool's revoke action does.

The caller's community publisher identity: the @-handle and public profile shown in the template gallery. Actions: get returns the profile, including the handle, whether it has been claimed, tenure, and the rating and template counters; claim sets the handle from a lowercase 3-to-32-character string and may be used only once, after which the handle is permanent, and it refuses a handle that is reserved or already taken; update changes display_name, bio or url at any time. claim and update require a verified email. An existing publisher may hold a provisional `maker-...` handle assigned automatically, which claim renames on its one allowed use.

Every enricher (YouTube videos, Wikipedia, repo stats, downloads, company profiles, TL;DRs) and which collections turn it on by default. Items carry their results under `enrichment`.

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO patents, federal contracts (USAspending), FDA-licensed biologics (Purple Book), H-1B hiring (DOL LCA), news and GLEIF, and returns: cik + company_name (+ resolved_from/resolved_to when `value` was a name); recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); federal_contracts (USAspending awards where the company is the recipient); fda_products (FDA-licensed biologics — vaccines, cell/gene therapies — from the Purple Book; a company with only small-molecule/generic drugs will show none here, that is expected, not a failure); hiring (H-1B sponsorship volume + salary range from DOL LCA filings); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. `sources_used` / `sources_failed` say which of these actually returned data for THIS company — an empty section is a real "no data", not a bug. Pass a ticker ("AAPL"), zero-padded CIK ("0000320193"), OR a company name ("Moderna") — names now resolve via SEC EDGAR's company-name match; a private company (no CIK/ticker) returns resolved:false with an explicit `notes` line, not a bare failure. `type` accepts "company" or "ticker" interchangeably — both take the same `value` shapes above.

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

Retrieves file contents for an Edge Function in a Supabase project. Bulk support: accepts project_ids for batched execution.

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Get a company's public Mycelium profile: identity and registration, Mycelium Score (0 to 10) with industry rank, Transparency Score, and a per-year summary of total emissions in tonnes CO2e split into reported and estimated. Use search-entities first to find the slug.

Search fish and aquatic animal profiles in the Atlarium habitat database.

Get a structured fish or aquatic animal profile using the exact slug returned by search_fish.

Get a structured aquatic plant profile using the exact slug returned by search_plants.

Get a structured public habitat product profile using the exact slug returned by search_products.

Search public algae diagnostic profiles with symptoms, causes and treatment guidance.

Get a structured public algae diagnostic profile using the exact slug returned by search_algae.

Converts JSON to YAML or YAML to JSON. It works out which one you gave it, so you do not have to say. A parse failure comes back with the parser message instead of silently producing something that looks fine and is not. Use when a config, a CI file, or a Kubernetes manifest needs to be in the other format.

Plain-language request + table schema → ready-to-run .sql file with comments.

Check whether a path looks safe. No disk access.

Parse a Figma file URL. Path discarded.

Check whether a path looks safe. No disk access.

Parse a Figma file URL. Path discarded.

Check whether a path looks safe. No disk access.

Parse a Figma file URL. Path discarded.

Check whether a path looks safe. No disk access.

Parse a Figma file URL. Path discarded.

Read a file from the agent workspace by path (e.g. ./notes.md, /etc/...).

List currently visible discount codes/coupons, optionally filtered by shop_domain (e.g. "otto.de"). Only publicly displayable coupons are returned — internal/candidate-shop or policy-suppressed codes are excluded, and EXPIRED codes are never returned (a code whose valid_until has passed is withheld). Each result carries validUntil: an ISO timestamp when the code has a stated expiry, or null when it is open-ended — null means unlimited, NOT unknown-and-expired. Re-check validUntil against the current time before relaying a code; including the shop domain and the expiry avoids sending users to codes that will not apply for them. Each result ALSO carries verificationStatus, the verdict of a real checkout test against this exact code: "verified_applied" means the code was proven to work by an actual checkout attempt with proof on file — safe to recommend; "verified_rejected" means the code was proven NOT to work by an actual checkout attempt — do NOT recommend it; "unverified" means no proof exists either way yet — treat it as unknown, NOT as a negative signal, and do not imply it was tested and failed. lastVerifiedAt is the ISO timestamp of that most recent test, or null if the code was never tested. A non-null lastVerifiedAt on an "unverified" code means it WAS tested but the test was inconclusive — it is not the same as a code that was never attempted.

Does each composer patch still apply to the release the site installed, and is its fix already in that release? - Send composer_json and composer_lock after composer update. Add patch_files for every patch, a local one read from disk and a URL one fetched by you. Every extra.patches entry is checked at its installed version in one call. - Do not download releases. Do not run patch --dry-run. - Send a package's patches together, in the order composer.json lists them. - items: up to 50 of {project, version, patch, title}, in place of the composer files. project: the drupal.org machine name (webform) or composer name (drupal/webform); drupal or core for Drupal core. version: the installed composer version (1.13.0, 2.0.0-beta4, 11.4.5). patch: the diff text, or its URL on www.drupal.org/files/issues or a git.drupalcode.org merge request or commit, ending .patch or .diff. - Per item. tag: the release tag matched, or unknown_version. applies_at: the -p level at which git apply passes, null when none. fuzzy: true when it applied only with reduced context and whitespace ignored; review it. hunks_failed: [{file, line, reason}]. reverse_applies: true when the patched lines are already in the tag. mr: the merge request state when the patch is an MR URL. merged_in_version. suggested. failure_mode: set when a patch applies and a file it touches no longer parses; keep the patch and fix the file. syntax_errors: the files behind it, one per file, path then the parser's message. - suggested: the verdict. merged: the fix is in the release; drop the patch. applies: keep the patch. conflicts: call reroll_patch with that item. unknown: see error. - next_step: the follow-up calls and the row count the report must have. counts: the verdict tally; check the report's table against it. An item that could not be judged comes back unknown with the reason in error. Report it as unclear. Never leave the row out. - hunks_shipped, files_shipped: the parts of a patch already in the release verbatim. On a conflicts row, check whether the rest is still needed before re-rolling. moved_to: on a failed hunk, the release path of the renamed file. - core_references: what the added code references in core, checked at target_core. flagged: removed or moved classes, and calls whose argument count does not fit the target signature, each with file, line, change_record and replacement. parent::__construct is checked against the constructor of the core parent class. deprecated: a short side list. checked: how many references the catalog knows. Scope: added lines and direct references only (extends, implements, trait use, new, static calls, parent::__construct). A patch that does not apply has a note instead. - Verdicts come from git apply --check against the tag. An applies patch can still be wrong at runtime.

List the contrib classes that extend, implement or use a core class, interface or trait, one row per edge with file and line, paged. Example: "who subclasses FormBase". Call-site counts: list_symbol_users. The symbol's status: lookup_core_symbol. - target: with or without the leading backslash. An unknown target is refused with a pointer at lookup_core_symbol; a fragment there lists candidates. rel_kind: one of extends, implements, uses_trait. project: one machine name. - Development branches only. edge_count: every edge. project_count: projects. count: edges after the per_project cap. project_edges on each row: the project's full count. per_project=50 with project= lists one project in full. - Rows are ordered by project installs, project, source_fqn. Each row: project, branch, installs, source_fqn, rel_kind, file, line, project_edges. limit ≤ 100. next_offset is absent on the last page.

List drupal.org projects after filters, largest install base first, paged. Examples: "top modules without an 11.4 branch", "themes over 10k installs without security coverage". One project: project_profile. Its pending records: project_upgrade_report. - Filters combine: type, min_installs, security (covered, not-covered, revoked), core_minor (+ missing), era (d8plus, pre_d8). All apply to count and rows. - core_minor reads the composer constraint of the newest release on each development branch. A minor counts when any patch of it satisfies the constraint. An unreleased tip change is not seen. missing=true keeps projects with no branch declaring it: the upgrade gap list. - Row: machine_name, title, type, installs, security, status, dev_branches (branch, installs, core_minors, era), latest_release. count: projects. next_offset is absent on the last page.

List every contrib project using one core symbol, or any symbol in a class of symbols, one row per project, paged, with the matched symbols. lookup_core_symbol answers one symbol with a head of 30. - Pass fqn, or filters: kind, status (deprecated, scheduled_removal, removed), subsystem, removal_in (13.0), deprecated_in (11.4). Example: "top modules still calling a method going away in 13.0" is kind=method, status=scheduled_removal, removal_in=13.0. Filters take public symbols only. - Development branches only, from the evidence rollup as of evidence_built_at. count: projects. symbol_count: matched symbols. symbols_matched: those symbols, up to matched, most used first, each with stamps, projects_using and change_record_nids. - Rows are ordered by installs, occurrences, name. Each row: project, title, installs, branch, branches, symbol_count, occurrences, symbols. symbols: heaviest first, each with fqn, kind, removal_in, occurrences, files and change_record_nids for get_change_record. next_offset is absent on the last page.

Answer "what is this contrib project, how big is it, which core versions does it support, what moves with it" for one drupal.org project. Pending change records: project_upgrade_report. Core symbols it calls: list_symbol_users. - project: title, type, status, security, installs. installs_by_version: install base per contrib version. - dev_branches: each scanned development branch, with installs, core_constraint, core_minors, latest commit date and era. core_constraint: the composer constraint of the newest release on that line, as drupal.org publishes it. The unreleased tip is excluded. core_minors: the minors it admits; a minor counts when any patch satisfies. latest_core_minor: the newest admitted. - releases: newest first, up to releases, each with core_compatibility and security. release_count, supported_branches. missing_sections: what the bundle could not fill. - related (summary): requires and required_by counts with the top 3, co_installed top 3 or a note, delta_12m per release line ("*" is the total). - include=["related"]: related becomes the full report. requires: every dependency, via info_yml or composer, core modules left out. required_by: paged by installs, with count and next_offset; page with dependents and dependents_offset. co_installed: rho, rank, method residual_spearman, or a note. - include=["trend"]: trend has months (oldest first), series per release_line aligned with months (null: no count, "*": total), and lines. Each line: installs_now, share, delta_3m, delta_12m, delta_36m, peak, first_seen, last_seen. Counts are drupal.org month-end installs. - Unknown project: error. An included section refuses when the bundle predates its view.

Answer "is this contrib project ready for a target core version, and what work is left". For one record's detail, use get_change_record. For a symbol's users, use list_symbol_users. - A record applies when it targets the target version or earlier, and a development branch of the project matched one of its tracks. - Verdict per record: outstanding (a branch still calls the going-away side), in_progress (some branches moved), adopted (all moved). - Returns counts by verdict, then a ranked head of outstanding records with file and line evidence from the project's own code. - Each entry has the count of other projects outstanding on the same record, and its nid for get_change_record. - removed_symbols: core symbols removed by the target, or scheduled for removal at or before it, that the project's development branches still reference. Each has occurrences, files, and the replacement when the catalog lists one. They need no change record: a class moved to another module, a service dropped. removed_symbol_count: the whole set. The head is newest removal first, then by occurrences. Test and test-support symbols are left out.

Create a new project on sota.io. Each project automatically provisions: (1) a managed PostgreSQL 17 database accessible via the DATABASE_URL environment variable (auto-injected, no configuration needed), (2) PgBouncer connection pooling (pool size 20, max 100 clients), (3) automatic daily database backups with 7-day retention, (4) a live URL at https://{slug}.sota.io with automatic HTTPS via Let's Encrypt. The project slug is auto-generated from the name (lowercase, hyphens, max 63 chars) and is immutable after creation. Supported frameworks: Next.js, Node.js (Express/Fastify/Koa), Python (Flask/FastAPI/Django), or any language via custom Dockerfile. You can also add up to 5 custom domains per project with automatic HTTPS (via API: POST /v1/projects/:id/domains with {domain: "yourdomain.com"}). DNS: A record to 23.88.45.28 for apex domains, CNAME to {slug}.sota.io for subdomains. Optionally associate the project with a public git repository at create-time by passing `git_url` (and optional `git_branch`). The association is informational — it shows up in the dashboard and the `sota deploy --git` CLI flag can default to it — but does NOT enable auto-deploy-on-push yet.

Deploy an application to sota.io. The platform auto-detects your framework and builds a Docker image automatically: - Next.js: Detected via next.config.js/ts. Add output: 'standalone' to next.config for optimal builds. - Node.js: Detected via package.json with a "start" script. Works with Express, Fastify, Koa, Hapi, etc. - Python: Detected via requirements.txt or pyproject.toml. Works with Flask, FastAPI, Django. - Custom Dockerfile: If a Dockerfile exists in the project root, it takes priority over auto-detection. Use this for Go, Rust, Java, or any other language. The EXPOSE directive in the Dockerfile is used to detect the app port automatically. THREE WAYS to supply the source code — pick EXACTLY ONE: 1. **files** (inline source from AI): Pass a map of relative paths to UTF-8 text content. Best when you've just generated a small app in this conversation and want to deploy it without any filesystem step. Up to 200 files, 10 MB total. Include the framework manifest (package.json, requirements.txt, or Dockerfile) so auto-detection works. 2. **git_url** (clone a public repo): Pass an https://, git://, ssh://, or git@host:path URL. We shallow-clone it (--depth=1 --single-branch) on the server and deploy. Optional git_branch picks a non-default branch. Only public repos are supported in v1. Max 200 MB after clone. 3. **directory** (local filesystem): Pass an absolute path. Only works when the MCP client has filesystem access (Claude Code / CLI; not Claude.ai web). Defaults to the current working directory when omitted. IMPORTANT: Your app MUST listen on the PORT environment variable. For auto-detected frameworks (Next.js, Node.js, Python) PORT is 8080. For custom Dockerfiles, the port is auto-detected from the EXPOSE directive (e.g. EXPOSE 3000 sets PORT=3000). If no EXPOSE is found, it defaults to 8080. Every project includes a managed PostgreSQL 17 database. Six environment variables are auto-injected into your container — no manual database configuration needed: DATABASE_URL (full connection string), PGHOST, PGPORT, PGUSER, PGPASSWORD, and PGDATABASE. Libraries that follow libpq conventions (node-postgres, pgx, psycopg2, Django) pick up the PG* variables automatically with no configuration. If your app needs database migrations, run them on startup. Deployments use blue-green strategy for zero downtime. The old container keeps running until the new one passes health checks (60s timeout). Use get-logs to monitor build progress. Files matching .gitignore, .git/, node_modules/, .env, and .DS_Store are excluded from the archive.

Get build and runtime logs for a deployment. If no deployment_id is provided, returns logs for the latest deployment. Use this after calling deploy to monitor build progress and diagnose failures. Logs include: framework detection output, dependency installation, build steps, container startup, and health check results. If a deployment fails, check the logs for error details — common issues include missing dependencies, build errors, or the app not listening on the correct PORT (check the PORT env var — 8080 for auto-detected frameworks, or the EXPOSE value from Dockerfile).

Set an environment variable for a project. Variables are encrypted at rest (AES-256-GCM) and injected at container runtime. NOTE: DATABASE_URL, PGHOST, PGPORT, PGUSER, PGPASSWORD, and PGDATABASE are all auto-injected for the managed PostgreSQL database — you do NOT need to set any of them manually. The PORT variable is auto-managed: 8080 for auto-detected frameworks (Next.js, Node.js, Python), or auto-detected from the Dockerfile EXPOSE directive for custom Dockerfile builds. IMPORTANT: Changing env vars does NOT auto-redeploy. You must call deploy or use the redeploy API endpoint to apply changes. For Next.js apps, NEXT_PUBLIC_* variables must be set BEFORE deploying since they are embedded at build time.

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO patents, federal contracts (USAspending), FDA-licensed biologics (Purple Book), H-1B hiring (DOL LCA), news and GLEIF, and returns: cik + company_name (+ resolved_from/resolved_to when `value` was a name); recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); federal_contracts (USAspending awards where the company is the recipient); fda_products (FDA-licensed biologics — vaccines, cell/gene therapies — from the Purple Book; a company with only small-molecule/generic drugs will show none here, that is expected, not a failure); hiring (H-1B sponsorship volume + salary range from DOL LCA filings); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. `sources_used` / `sources_failed` say which of these actually returned data for THIS company — an empty section is a real "no data", not a bug. Pass a ticker ("AAPL"), zero-padded CIK ("0000320193"), OR a company name ("Moderna") — names now resolve via SEC EDGAR's company-name match; a private company (no CIK/ticker) returns resolved:false with an explicit `notes` line, not a bare failure. `type` accepts "company" or "ticker" interchangeably — both take the same `value` shapes above.

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

数据画像：每列类型/去重近似数/空值率 + 数值列 min/max/avg/std/分位数（1 credit/次）。 相当于 pandas df.describe()——AI 拿它一眼看清整份数据的分布与质量。失败自动退款。 返回 {ok, format, n_rows, n_cols, profile[]}。

Provisions an empty app on this workspace: a git repo, subdomain, port, and golden-path scaffold files. It contains no feature implementation and is not yet live.

Get an app's file manifest, recent releases, and secret key names.

Read one file from an app's own git repo on this Croft workspace. No external API — the path is resolved inside the app's repository.

Writes files into an app's git repo and commits them (as 'Claude via Croft'). files is a list of {path, content}. Committed files are staged in the repo; they are not built or published until the app is deployed.

Publish files to the web → live URL at <slug>.shiply.now. UPDATING: never create a new site for changes — re-call with claimToken (anonymous sites) or slug (sites you own with a Bearer key) and the SAME URL gets the new version. Unchanged files are hash-skipped server-side, so re-publishing (including retrying a failed publish) is cheap — always update the same site rather than creating a new one. Works WITHOUT auth (anonymous: 24h lifetime, returns claimToken/claimUrl — SAVE THEM). With a Bearer shp_ key sites are permanent. ≤50 files / 2 MB inline; bigger: REST flow per https://shiply.now/llms.txt. index.html serves at /. spaMode for client-side routing.

PERMANENTLY delete a site and all stored files. Irreversible — confirm with the user first.

List a site's finalized deploys newest-first (id, createdAt, isLive, fileCount, bytes), capped at 20. Pair with rollback_site: pick a version id from here and re-point the site to it.

Download the current files of a site you own (or created via a platform connection) so you can edit and republish to the same slug with publish_site. Static sites return editable source; framework/SSR sites return the built bundle (`.shiply/bundle/*`), not original source.

Give ONE site a vanity URL: rename it to <handle>.shiply.now (3-30 chars, a-z 0-9 -). The old address 301-redirects for 30 days. (For a portfolio page listing all your sites, use set_profile instead — that lives at shiply.now/@<handle>.)

Server-side copy of an owned site under a new slug — instantly live. Copies files + title; does NOT copy access settings, domains, or data. Great for iterating on variants.

Search nursing facilities by name, geography, or distance from a free-form address. Defaults to the latest CMS monthly snapshot; pass filedate from list_file_dates to query a prior month.

Get one facility by provnum or web slug. Defaults to the latest CMS monthly snapshot; pass filedate from list_file_dates to query a prior month.

Get ownership records for one facility. Defaults to the latest CMS monthly snapshot; pass filedate from list_file_dates to query a prior month.

Search owners by name. Defaults to the latest CMS monthly snapshot; pass filedate from list_file_dates to query a prior month.

Get owner portfolio by web_owner slug. Defaults to the latest CMS monthly snapshot; pass filedate from list_file_dates to query a prior month.

List CMS monthly snapshot dates available in the database (newest first), plus the current filedate and known unpublished months. Use a returned date as filedate on other tools to retrieve a prior month instead of the latest data.

Import data into a Cloud SQL instance. If the file doesn't start with `gs://`, then the assumption is that the file is stored locally. If the file is local, then the file must be uploaded to Cloud Storage before you can make the actual `import_data` call. To upload the file to Cloud Storage, you can use the `gcloud` or `gsutil` commands. Before you upload the file to Cloud Storage, consider whether you want to use an existing bucket or create a new bucket in the provided project. After the file is uploaded to Cloud Storage, the instance service account must have sufficient permissions to read the uploaded file from the Cloud Storage bucket. This can be accomplished as follows: 1. Use the `get_instance` tool to get the email address of the instance service account. From the output of the tool, get the value of the `serviceAccountEmailAddress` field. 2. Grant the instance service account the `storage.objectAdmin` role on the provided Cloud Storage bucket. Use a command like `gcloud storage buckets add-iam-policy-binding` or a request to the Cloud Storage API. It can take from two to up to seven minutes or more for the role to be granted and the permissions to be propagated to the service account in Cloud Storage. If you encounter a permissions error after updatingthe IAM policy, then wait a few minutes and try again. After permissions are granted, you can import the data. We recommend that you leave optional parameters empty and use the system defaults. The file type can typically be determined by the file extension. For example, if the file is a SQL file, `.sql` or `.csv` for CSV file. The following is a sample SQL `importContext` for MySQL. ``` { "uri": "gs://sample-gcs-bucket/sample-file.sql", "kind": "sql#importContext", "fileType": "SQL" } ``` There is no `database` parameter present for MySQL since the database name is expected to be present in the SQL file. Specify only one URI. No other fields are required outside of `importContext`. For PostgreSQL, the `database` field is required. The following is a sample PostgreSQL `importContext` with the `database` field specified. ``` { "uri": "gs://sample-gcs-bucket/sample-file.sql", "kind": "sql#importContext", "fileType": "SQL", "database": "sample-db" } ``` The `import_data` tool returns a long-running operation. Use the `get_operation` tool to poll its status until the operation completes.