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

Search official Microsoft/Azure documentation to find the most relevant and trustworthy content for a user's query. This tool returns up to 10 high-quality content chunks (each max 500 tokens), extracted from Microsoft Learn and other official sources. Each result includes the article title, URL, and a self-contained content excerpt optimized for fast retrieval and reasoning. Always use this tool to quickly ground your answers in accurate, first-party Microsoft/Azure knowledge. ## Follow-up Pattern To ensure completeness, use microsoft_docs_fetch when high-value pages are identified by search. The fetch tool complements search by providing the full detail. This is a required step for comprehensive results.

Search for code snippets and examples in official Microsoft Learn documentation. This tool retrieves relevant code samples from Microsoft documentation pages providing developers with practical implementation examples and best practices for Microsoft/Azure products and services related coding tasks. This tool will help you use the **LATEST OFFICIAL** code snippets to empower coding capabilities. ## When to Use This Tool - When you are going to provide sample Microsoft/Azure related code snippets in your answers. - When you are **generating any Microsoft/Azure related code**. ## Usage Pattern Input a descriptive query, or SDK/class/method name to retrieve related code samples. The optional parameter `language` can help to filter results. Eligible values for `language` parameter include: csharp javascript typescript python powershell azurecli al sql java kusto cpp go rust ruby php

Retrieves full documentation content for Svelte 5 or SvelteKit sections. Supports flexible search by title (e.g., "$state", "routing") or file path (e.g., "cli/overview"). Can accept a single section name or an array of sections. Before running this, make sure to analyze the users query, as well as the output from list-sections (which should be called first). Then ask for ALL relevant sections the user might require. For example, if the user asks to build anything interactive, you will need to fetch all relevant runes, and so on. Before calling this tool, try to implement Svelte components using your own knowledge and the `svelte-autofixer` tool, since calling this tool is token intensive.

Lists all available Svelte 5 and SvelteKit documentation sections in a structured format. Each section includes a "use_cases" field that describes WHEN this documentation would be useful. You should carefully analyze the use_cases field to determine which sections are relevant for the user's query. The use_cases contain comma-separated keywords describing project types (e.g., "e-commerce", "blog"), features (e.g., "authentication", "forms"), components (e.g., "slider", "modal"), development stages (e.g., "deployment", "testing"), or "always" for fundamental concepts. Match these use_cases against the user's intent - for example, if building an e-commerce site, fetch sections with use_cases containing "e-commerce", "product listings", "shopping cart", etc. If building a slider, look for "slider", "carousel", "animation", etc. Returns sections as "* title: [section_title], use_cases: [use_cases], path: [file_path]". Always run list-sections FIRST for any Svelte query, then analyze ALL use_cases to identify relevant sections, and finally use get_documentation to fetch ALL relevant sections at once.

Search the OrchestKit documentation. Use this first to find the right page for a question. Input: a query string. Returns a ranked list of pages with titles and URLs.

Convert one or more cURL commands or HAR (HTTP Archive 1.2) JSON traces into a valid, production-ready Apache JMeter .jmx test plan XML with HTTP Request Defaults, Header Managers, Cookie Managers, timeouts, and assertions. Supports GET, POST, PUT, DELETE, PATCH, and RFC 9838 QUERY methods.

Search nifra's framework documentation and get back ONLY the matching sections - auth, uploads, ISR, WebSockets, loaders, deployment, anything. Call with no query for the cheap section index; pass query (e.g. "isr revalidate") for the top matching sections. Use this instead of reading llms-full.txt (~150 KB) whole. For the EXACT TypeScript of a type/interface/function, call nifra_types instead (don't read .d.ts files).

Get a VERIFIED, copy-pasteable nifra code example for a task - auth route, file upload, ISR page, loader/action, typed client, SSE, deployment, etc. Every snippet is typechecked against the installed nifra version, so it compiles as-is. PREFER THIS over writing nifra code from memory (training data drifts). Returns code as TEXT for direct use; to visually browse the whole example set instead, use nifra_gallery. Call with no query for the grouped index; pass query (e.g. "protected route", "upload", "isr revalidate") for matching snippets.

Get the EXACT TypeScript declaration of any exported @nifrajs/* symbol - interface, type, class, function, const. Each signature is generated from the package's built .d.ts, so it is the LITERAL declaration: complete, authoritative, never prose and never truncated. THIS IS THE SOURCE OF TRUTH for nifra's types - do NOT read node_modules/@nifrajs/**/*.d.ts; call this instead. Pass `name` for an exact symbol (e.g. "RateLimitStore", "RouteSchema", "Context", "rateLimit"); pass `query` to search by keyword; omit both for the per-package index of names. A `name` lookup is always the complete declaration; a `query` returns a one-line summary plus the signature, collapsing an oversized body - pass `full: true` to override.

Open an interactive, filterable gallery of ALL of nifra's verified code examples (MCP Apps widget) - for browsing and discovering what exists. NOT for fetching one snippet as text: use nifra_example for that. Pass query to pre-filter; the widget also filters client-side.

[Requires authentication] Call the authenticate tool first to start or confirm 1inch Business login (initialize 200 is still anonymous). If authenticate or this tool returns HTTP 401, complete OAuth, then retry. Limit orders via the 1inch Orderbook API (v4.1). IMPORTANT: The "action" parameter is REQUIRED. Must be one of: "build", "create", "list", "cancel". Actions with example parameters: 1. build (recommended first step): { "action": "build", "chain": 1, "makerAsset": "0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48", "takerAsset": "0xdAC17F958D2ee523a2206206994597C13D831ec7", "makingAmount": "1000000", "takingAmount": "990000", "makerAddress": "0x..." } Optional: expirationSeconds (default 604800 = 7 days). With an active WalletConnect session, the order is signed and submitted automatically (set execute=false to return typed data only). 2. create (after signing typedData from build): { "action": "create", "chain": 1, "orderHash": "0x...", "signature": "0x...", "orderData": { ... } } 3. list (query orders): - By maker: { "action": "list", "chain": 1, "listMode": "by_maker", "makerAddress": "0x..." } - By hash: { "action": "list", "chain": 1, "listMode": "by_hash", "orderHash": "0x..." } - Browse: { "action": "list", "chain": 1, "listMode": "all", "limit": 10 } 4. cancel (inspect + guidance): { "action": "cancel", "chain": 1, "orderHash": "0x..." } Typical flow: build -> sign typedData -> create (or one build call when WalletConnect is connected — order signed and submitted automatically). The maker asset may require a one-time ERC-20 approval for the Limit Order Protocol; it costs native gas even though the limit order itself is gasless. When a build response includes an "approval" block, tell the user upfront (approval.estimatedCost holds the estimated cost in native units) and broadcast the included approveTx before signing. With WalletConnect, the approve is sent automatically — "approvalTxSent": true means the first wallet prompt was the one-time approval. Requires authentication. For raw HTTP access, use product_api.

[Requires authentication] Call the authenticate tool first to start or confirm 1inch Business login (initialize 200 is still anonymous). If authenticate or this tool returns HTTP 401, complete OAuth, then retry. Call any 1inch product API endpoint using the authenticated user's credentials (base URL is the unified gateway, e.g. https://api.1inch.com). Call authenticate first. Anonymous sessions get HTTP 401 (OAuth), not x402. After a real org login, quota-exhausted routes may return a PaymentRequired tool result; retry with a signed payment in _meta["x402/payment"] (batch-settlement scheme only — see file://1inch-mcp/guides/x402-payments). Do not treat PaymentRequired as login. Optional: if your client can read MCP resources, file://1inch-mcp/guides/api-index has live Swagger links and extra gateway notes (mirrors business.1inch.com/portal/llms.txt). Common chain IDs: Ethereum=1, BNB=56, Polygon=137, Arbitrum=42161, Optimism=10, Base=8453, Avalanche=43114, Gnosis=100, zkSync=324, Linea=59144, Sonic=146, Unichain=130, Cronos=25, Monad=10143, Solana=501 (where applicable). Gateway products (use these path prefixes with this tool): - Portfolio: /portfolio/portfolio/v5.0/... — example path="/portfolio/portfolio/v5.0/general/current_value", query={"addresses":"0x..."}; token metrics path="/portfolio/portfolio/v5.0/tokens/metrics", query={"addresses":"0x...","timerange":"1year"} - Balance: /balance/v1.2/{chainId}/... — example path="/balance/v1.2/1/balances/0x..." - Spot Price: /price/v1.1/{chainId} — example path="/price/v1.1/1", method="POST", body={"tokens":["0x..."],"currency":"USD"} - Token: /token/v1.4/{chainId}/... — example path="/token/v1.4/1/search", query={"query":"USDC"} (prefer v1.4; older v1.2 chain search is deprecated in OpenAPI) - Token Details: /token-details/v1.0/details/{chain}/{tokenAddress} — example path="/token-details/v1.0/details/1/0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48" - Gas Price: /gas-price/v1.6/{chainId} — example path="/gas-price/v1.6/1" - Swap (Classic): /swap/v6.1/{chainId}/... — example path="/swap/v6.1/1/quote", query={"src":"0x...","dst":"0x...","amount":"..."} (exact query names per OpenAPI) - Orderbook: /orderbook/v4.1/{chainId}/... — example path="/orderbook/v4.1/1/all", query={"page":"1","limit":"10"} - Fusion (Intent): /fusion/orders/v2.0/..., /fusion/quoter/v2.0/..., /fusion/relayer/v2.0/... — example path="/fusion/quoter/v2.0/1/quote/receive" with required query params from spec - Fusion+ (Cross-chain): /fusion-plus/orders/..., /fusion-plus/quoter/..., /fusion-plus/relayer/... — example path="/fusion-plus/quoter/v1.2/quote/receive" with required params; equivalent routes also exist under /cross-chain/orders|quoter|relayer - History: /history/v2.0/history/{address}/events — example path="/history/v2.0/history/0x.../events", query={"chainId":"1","limit":"50","tokenAddress":"0x..."} (optional tokenAddress filters by contract; response shape uses items[].details.txHash — not raw event logs) - Traces: /traces/v1.0/chain/{chainId}/block-trace/{blockNumber}/tx-hash/{txHash} — example path="/traces/v1.0/chain/1/block-trace/18000000/tx-hash/0x..." (not /transaction/{hash}) - NFT: /nft/v2/... — example path="/nft/v2/byaddress", query={"chainIds":"1","address":"0x..."} - Charts: /charts/v1.0/chart/line/{token0}/{token1}/{period}/{chainId} — example path="/charts/v1.0/chart/line/0x.../0x.../24H/1" (period: 24H, 1W, 1M, 1Y, AllTime; not a separate timerange query) - Domains: /domains/... — example path="/domains/v2.0/lookup", query={"name":"vitalik.eth"} - Aqua (strategy analytics): /aqua/v1.0/strategies/... — example path="/aqua/v1.0/strategies/opened", query={"limit":"100"}; maker stats path="/aqua/v1.0/strategies/makers/0x.../stats". Prefer the dedicated "aqua" tool when Unleash flag mcp-service.tool.aqua is enabled; otherwise use product_api for raw HTTP. - Tx Gateway: /tx-gateway/... — example path="/tx-gateway/v1.1/1/broadcast", method="POST", body={...} - Web3 RPC: /web3/{chainId}/... — JSON-RPC over HTTP POST to an EVM (or Solana 501) node; Gateway exposes e.g. 1,10,25,56,100,130,137,143,146,324,501,8453,42161,43114,59144 — confirm availability for your org/plan. Example path="/web3/1", method="POST", body={"jsonrpc":"2.0","id":1,"method":"eth_blockNumber","params":[]} Gotchas: Portfolio gateway path repeats "portfolio" (/portfolio/portfolio/v5.0/...) because the gateway strips the first segment. Spot Price returns WEI in native currency unless you set currency. Token list responses are large; prefer search. Token Details does not support native ETH pseudo-address 0xeeee...eeee; use WETH. Balance responses may include zero balances—filter client-side. For limit order flows (build, sign, create, cancel), prefer the "orderbook" tool. For swap execution, prefer the "swap" tool. Use product_api for direct REST access to any endpoint.

Query the 1inch Aqua API (v1.0) — analytics for Aqua strategies (shared-liquidity market making): maker stats, strategy lists, overview, activity, and volume series. Read-only. No OAuth required. REQUIRED: "action" — read actions (no OAuth): maker_stats, list_maker_strategies, strategy_overview, strategy_activity, strategy_volume, list_opened. Read the resource file://1inch-mcp/guides/aqua-workflow for per-action examples, priceRange semantics, and maker/taker flows. Raw HTTP: product_api with path "/aqua/v1.0/strategies/...".

[Requires authentication] Call the authenticate tool first to start or confirm 1inch Business login (initialize 200 is still anonymous). If authenticate or this tool returns HTTP 401, complete OAuth, then retry. Look up production API request logs for your 1inch Business organization to troubleshoot integration issues. Results are always scoped to your authenticated organization. Two modes: 1) By request id: pass requestId (the x-request-id header returned on 1inch API responses). Optionally narrow startTime/endTime (defaults: last 24 hours ending now). 2) Logs in a time window: omit requestId and pass both startTime and endTime (RFC3339). Optionally set logLevel ("info", "warn", or "error") to filter by severity; omit to return all levels. Limits: each call covers at most a 24-hour window; how far back you can query depends on your plan's log retention.

Keyword and semantic search across the connected repository's generated docs, conventions, documentation gaps, AI-context notes, and indexed code. Read-only; no side effects. Returns ranked matches in Markdown grouped into Documentation and Code sections, each with a title, snippet, and source paths. Use for open-ended lookups when you don't know which category holds the answer; when you do, the specific getters (get_conventions, get_doc_gaps, get_documentation_opportunities) are more direct. Omitting query returns recent context instead.

List the repository's generated documentation as a browsable table of contents - every doc page, not a query-filtered subset. Read-only; no side effects. Returns Markdown grouped by section, each entry with its title, slug, repository path, and source paths, plus the total count and a pagination cursor so you can tell whether more pages remain (no silent truncation). Use this to see what docs already exist before adding one (so you don't duplicate) or to find the slug to pass to propose_doc_update; when you are hunting for a specific topic, search_docs is more direct.

Search Mapbox documentation by keyword or natural language query. Searches across API reference, GL JS, Help Center, Style Spec, Studio, Search JS, iOS/Android Maps and Navigation SDKs, and Tilesets. Returns ranked results with titles, URLs, and descriptions. Use get_document_tool to fetch the full content of a result page.

Search the official @imqueue docs (guides, tutorial, CLI manual, articles) and every exported symbol of every @imqueue package that publishes a generated API reference, returning the most relevant pages with their URLs. Each result names the package it belongs to. Takes a plain question or an exact symbol name such as 'RedisQueue.send', 'PgPubSub.listen' or 'watcherCheckDelay'. Answers 'how do I do X in @imqueue' and confirms a signature before code is written against it. Every result carries the page URL, which get_doc reads in full. Some capabilities are covered by two mutually exclusive packages — @imqueue/pg-prisma vs @imqueue/pg-sequelize, @imqueue/opentelemetry vs @imqueue/datadog — so for a query like 'tracing' or 'database', call list_packages for the choosing rule rather than taking whichever package ranks first, and pass `package` here to search within the one you settled on.

查询指定公历日期的中国法定节假日或调休安排，同时返回农历信息。支持2025、2026年。参数date格式：YYYY-MM-DD

Search across the Cerebrium knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Cerebrium, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. `head -200 /api-reference/create-customer.mdx`).

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Cerebrium documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

Browse the SvGrid demo catalogue: id, title, category and a one-line blurb. Call with no arguments for the category index, then filter with `query` or `category`, then read one with get_example_source.

Searches Apple Notes by title or content. Paginated: `limit` is capped at 100 per call, so page with `offset` instead of asking for a bigger limit. The response carries `total` (how many notes match the query in all) and `has_more`, so a capped page is never mistaken for the complete answer — page until `has_more` is false, which is exact even when `total_is_estimated` says the count is only a lower bound. To walk every match, pass order="id" — see the order parameter.

Searches your Microsoft Teams chat and direct-message history (all conversations at once) by text, sender name, and/or date range. Use this to find where something was discussed in Teams without knowing which chat. Returns matching messages with the chat they came from. Provide at least one of query, from_sender, since, until.

Finds elements on the current page of a web session so you can decide what to click or type into. `query` is a CSS selector OR visible text to match. Returns up to 30 matches with tag/text/name/type/href — never a silent empty.

Waits (polls, not a fixed sleep) until an element appears on the page, or times out. Use for SPA pages that hydrate after load. Prefer `selector` (a CSS selector, e.g. "input[name=password]"). `condition` also accepts the form "document.querySelector('...')"; any OTHER JavaScript condition runs arbitrary code on the page (same power as web_eval) and is disabled when LMCP is in read-only mode. Returns met:true/false.

Search the official Redpanda documentation and return the most relevant sections from it for a user query. Each returned section includes the url and its actual content in markdown. Use this tool for all queries that require Redpanda knowledge. Results are ordered by relevance, with the most relevant result returned first. If you know the user's deployment platform, pass "platform" so results from the other platform's docs are excluded. Note that "platform" filters the sections already retrieved rather than re-running the search, so it can return substantially fewer sections: on a broker-level question where most matches come from the other platform's docs, it can cut a 15-section response to 1 or 2. Omit "platform" if you would rather have more context and judge platform relevance yourself from each section's url. Results are NOT restricted to one docs version: the same page can come back once per indexed version, so check each section's url before stating that something applies to a particular release.

Return origin, host, and path for a URL. Query and fragment are dropped.

Count characters in a search query. Query discarded.

Search across the DarkFunnels knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about DarkFunnels, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. `head -200 /api-reference/create-customer.mdx`).

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the DarkFunnels documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

Return origin, host, and path for a URL. Query and fragment are dropped.

Count characters in a search query. Query discarded.

Return origin, host, and path for a URL. Query and fragment are dropped.

Count characters in a search query. Query discarded.

Search across the SiteGPT Docs knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about SiteGPT Docs, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. `head -200 /api-reference/create-customer.mdx`).

Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the SiteGPT Docs documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

Return origin, host, and path for a URL. Query and fragment are dropped.

Count characters in a search query. Query discarded.

Fetch the authenticated Healthie account (the provider/user that owns the API key). Good first call to verify auth. Read-only. GraphQL: query currentUser.

Fetch the current organization / practice (name, NPI, contact, user counts). Read-only. GraphQL: query organization.

List patients/clients, optionally filtered by keyword search or active status. Read-only. GraphQL: query users(keywords, offset, page_size, should_paginate, active_status).

Fetch a single user (patient or provider) by id. Read-only. GraphQL: query user(id).

List appointments, optionally filtered by patient, provider, date range, time-filter or status. Read-only. GraphQL: query appointments(user_id, provider_id, filter, startDate, endDate, filter_by_appointment_status).

Fetch a single appointment by id. Read-only. GraphQL: query appointment(id).

Set or replace the availability rules on a calendar — buffer times before/after events and optional per-day working hours. When these rules are set, every availability query on this calendar automatically applies them (busy-block expansion for buffers, masking outside working hours). Upsert: overwrites any existing rules.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Find issues, optionally filtered by a text query (matches title), team key, workflow-state name, or assignee email. Read-only. GraphQL: query issues(filter, first).

Fetch a single issue by its UUID or human identifier (e.g. "ENG-123"), including description, state, assignee and recent comments. Read-only. GraphQL: query issue(id).

List the teams in the workspace (id, key, name). Use a team's id for linear_create_issue or its key for linear_search_issues. Read-only. GraphQL: query teams.

List projects in the workspace (id, name, state, progress, target date). Read-only. GraphQL: query projects.

List issues assigned to the current user (the API key's owner / OAuth actor) via viewer.assignedIssues. Read-only. GraphQL: query viewer { assignedIssues }.

List cycles (sprints), optionally scoped to a team by key, with number, name and start/end dates. Read-only. GraphQL: query cycles(filter).

Search across the documentation to fetch relevant content for a given query

Fetch the authenticated Parabol user (the token owner): id, preferredName, email, tier, and the team ids (tms) they belong to. Parabol GraphQL: query { viewer { ... } }. Requires the USERS_READ scope. Start here to discover your identity and team ids.

List the viewer's tasks (Relay connection), optionally filtered by team, user, status, archived state, or a text query. Paginate with `first` + the `after` DateTime cursor. Parabol GraphQL: viewer.tasks. Requires TASKS_READ.

Escape hatch: run an arbitrary Parabol GraphQL QUERY (read-only) against action.parabol.co/graphql with optional variables. Mutations are REJECTED — use the dedicated write tools or parabol_graphql for those. Useful for fields not covered by the curated read tools. Requires the matching read scope(s) on your token.

MUTATES Parabol data (potentially): escape hatch to run an arbitrary Parabol GraphQL operation — including any mutation — against action.parabol.co/graphql with optional variables. Use for operations not covered by the curated tools. Your token must carry the scope the operation requires. Prefer parabol_query for read-only calls.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

List HTAG public REST endpoints. Optional `tag` (e.g. 'Markets', 'Property', 'Spatial') and `query` (substring against path / summary) filters. Returns path, method, operationId, tags, and summary for each match.

Exact reference for one REST endpoint: every query parameter (name, type, description, required, default), a real sample request, and a truncated real sample response. Use the path as shown by list_endpoints, e.g. '/v2/search/car/active'.

Full-text style search across every published Approved Knowledge record — company, services, service areas, warranty, installation, inspection, failure-analysis, maintenance and business operations knowledge. Omit the query to receive the full index.