Tool search 101,866 tools · 5,225 live servers

Paid hosted discovery for SAP agents. Search and filter the current on-chain AgentAccount directory by query, wallet, protocol, capability, x402 endpoint presence, and cursor pagination. Use this for targeted agent discovery before calling per-agent fetch tools. SAP MCP context: Read-only SAP SDK wrapper against the configured Solana RPC and SAP program. Use these reads to inspect current chain state before mutating registry, payment, reputation, memory, or tool accounts. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Paid hosted global SAP agent directory read. Enumerates current on-chain AgentAccount PDAs and supports query, wallet, protocol, capability, x402 endpoint filtering, compact/full views, and cursor pagination. SAP MCP context: Read-only SAP SDK wrapper against the configured Solana RPC and SAP program. Use these reads to inspect current chain state before mutating registry, payment, reputation, memory, or tool accounts. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Get detailed information about a single NFT/asset via DAS. SAP MCP context: Protocol das; operation class read. Use for read-only DAS NFT and asset discovery by owner, creator, collection, or search query. Prefer DAS reads before Metaplex writes when validating existing assets for an agent profile, collection, or metadata update. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Get all NFTs/assets owned by a wallet via DAS (supports pagination). SAP MCP context: Protocol das; operation class read. Use for read-only DAS NFT and asset discovery by owner, creator, collection, or search query. Prefer DAS reads before Metaplex writes when validating existing assets for an agent profile, collection, or metadata update. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Get all NFTs/assets created by a specific creator via DAS. SAP MCP context: Protocol das; operation class read. Use for read-only DAS NFT and asset discovery by owner, creator, collection, or search query. Prefer DAS reads before Metaplex writes when validating existing assets for an agent profile, collection, or metadata update. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Get all NFTs in a collection via DAS. SAP MCP context: Protocol das; operation class read. Use for read-only DAS NFT and asset discovery by owner, creator, collection, or search query. Prefer DAS reads before Metaplex writes when validating existing assets for an agent profile, collection, or metadata update. SAP MCP execution guidance: Intent: read/discovery workflow. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

Get cryptocurrency prices from Korean exchanges (Upbit, Bithumb). Returns KRW-denominated prices, 24h volume, and change rate. 💰 Price: $0.002 USDC per call 💳 Payment: x402 micropayment on Base, Polygon, or Solana 🔧 Client: AgentCash, Pay.sh, or any x402 SDK 📖 Docs: https://api.printmoneylab.com/.well-known/x402 Args: symbol: Crypto symbol (e.g., BTC, ETH, XRP, SOL, DOGE) exchange: Exchange to query — 'upbit', 'bithumb', or 'all' for both

Get all available trading symbols on Korean exchanges. Returns symbols available on Upbit, Bithumb, and those common to both. Use this to check which symbols you can query before calling other tools. 💰 Price: FREE (no x402 payment required)

Search tokens and trading pairs across all chains by name, symbol, or address, ranked with price, liquidity, and 24h volume. Send { query, limit? }. Find the right contract fast before sniping. [x402 paid tool — price $0.005; POST /api/snipe/search]

Find protocols that have tracked token-unlock schedules, by name substring. Send { query }. Use the returned slug with catalysts/unlocks. [x402 paid tool — price $0.005; POST /api/catalysts/search]

Prediction-market implied probabilities from Polymarket: search live event markets and get outcome probabilities, volume, and end date. Send { query, limit? }. Crowd-sourced odds for any event as a data feed. [x402 paid tool — price $0.005; POST /api/predict/odds]

Prediction-market arbitrage scanner: markets whose outcome prices sum below $1, implying a risk-free edge before fees. Send { query?, minEdgePct? }. [x402 paid tool — price $0.005; POST /api/predict/arb]

Robinhood Chain read-only eth_call: query any contract view function. Send { to, data, from? }. [x402 paid tool — price $0.005; POST /api/rhchain/call]

Bazaar Scout: independently measured health rankings of x402 services (uptime, latency, payment-terms validity). Query: limit, network, tag. [x402 paid tool — price $0.005; GET /api/scout/rankings]

Use this when you need a swap quote before trading tokens on-chain. Returns the best price across multiple DEXes in JSON. POST variant of dex_get_swap_quote -- same params passed as JSON body instead of query string. 1. bestDex: which DEX offers the best rate (Uniswap, SushiSwap, Aerodrome) 2. amountOut: expected output token amount 3. priceImpact: percentage price impact of the trade 4. minimumReceived: minimum output after slippage tolerance 5. route: swap path (e.g. USDC -> WETH -> TOKEN) 6. gasEstimateUsd: estimated gas cost in USD Example output: {"bestDex":"Uniswap V3","amountOut":"0.3215","priceImpact":"0.12%","minimumReceived":"0.3183","route":["USDC","WETH"],"gasEstimateUsd":0.04} Use this BEFORE executing any token swap to find the best rate and estimate slippage. Essential for trade sizing and DEX comparison. Do NOT use for gas estimation only -- use gas_get_current_price instead. Do NOT use for yield opportunities -- use defi_find_best_yields instead. Do NOT use for wallet balance -- use wallet_get_portfolio instead. Do NOT use for cross-chain bridging -- use bridge_find_best_route instead.

Use this when you need to check liquidity depth of a Solana DEX pool before trading. Returns TVL, slippage estimates, volume, and fee tier for pools matching a token mint. POST variant of solana_scan_pool_liquidity -- same params passed as JSON body instead of query string. 1. pools: array of DEX pools for the given token 2. Each pool contains: dex (Raydium/Orca/Meteora), pairName, tvlUsd, volume24h, feeTier, poolAge 3. depth: slippage estimates at 1%, 2%, 5% trade sizes in USD 4. bestPool: the pool with deepest liquidity 5. totalTvl: combined TVL across all pools for this token Example output: {"pools":[{"dex":"Raydium","pairName":"SOL/USDC","tvlUsd":45000000,"volume24h":12000000,"feeTier":0.25,"poolAge":"342d"}],"depth":{"1pct":500000,"2pct":950000,"5pct":2100000},"bestPool":"Raydium SOL/USDC","totalTvl":62000000} Use this BEFORE executing large swaps to estimate slippage. Essential for position sizing, liquidity analysis, and avoiding thin pools. Do NOT use for swap quotes -- use jupiter_get_swap_quote. Do NOT use for new token launches -- use solana_scan_new_tokens. Do NOT use for Solana fees -- use solana_get_priority_fees.

Get the daily price/volume history for a cryptocurrency over the last N days — for backtesting, charting, and trend analysis. PAID: $0.01 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Surface notable crypto flows — coins with unusually large 24h trading volume and high turnover (volume vs market cap), a proxy for whale activity. NOTE: this is VOLUME-DERIVED (method="volume_derived"), not raw on-chain transfer data, which requires a paid whale-tracking API. PAID: $0.01 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Get DeFi Total Value Locked (TVL) intelligence from DeFiLlama. With a protocol name, returns that protocol's TVL and 1d/7d changes; otherwise returns the top protocols by TVL grouped by category, plus total DeFi TVL. PAID: $0.01 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Scan the market for anomalies — unusual volume spikes (24h volume vs market cap), large 24h price moves, and price divergence from the 7d/30d moving averages. Returns ranked anomalies with a type and severity. The result carries a MINT provenance attestation so a buyer can verify it. PAID: $0.02 USDC per query after a daily free allowance. On a 402, pay the returned Solana memo and re-call with the SAME args plus payment_tx=<signature>. An Authorization: Bearer fnet_ key bypasses payment.

Fetch the latest headlines from the ritbit news feed (curated crypto / markets / business channels, newest first). Filter by `category` (crypto|markets|business) or explicit `channels`, and/or a free-text `query` (a ticker or keyword, matched in the post text and hashtags, e.g. BTC). Each item returns { source, url, publishedAt, tags (hashtags — where tickers appear), text }. There is NO importance field: judge impact yourself from the content (hacks, regulation, large moves, ⚠️ warnings). Use this to factor sentiment/catalysts into an assessment, or to answer "what's the latest?". Headlines are ru/en.

Search the PikaSim eSIM catalog (data eSIMs and phone-number eSIMs) by free-text query and/or ISO country code. Returns a list of matching plans, each with an id, a title (name + price), and a pikasim.com URL. Pass an id to the fetch tool for full details. Read-only.

Use this when you need to find the best DeFi yields for a token across all chains and protocols. Returns ranked opportunities in JSON. POST variant of defi_find_best_yields -- same params passed as JSON body instead of query string. 1. pool: pool/vault name and pair 2. protocol: protocol name (Aave, Compound, Lido, Aerodrome, etc.) 3. chain: which blockchain network 4. apy: current annual percentage yield 5. tvl: total value locked in USD 6. riskLevel: risk assessment (low/medium/high) 7. type: yield type (lending, staking, LP, vault) Example output: {"pools":[{"pool":"USDC Lending","protocol":"Aave V3","chain":"base","apy":4.82,"tvl":125000000,"riskLevel":"low","type":"lending"}],"token":"USDC","totalPools":15} Use this BEFORE deploying idle capital to find the highest safe yield. Essential for yield optimization and DeFi strategy comparison. Do NOT use for swap quotes -- use dex_get_swap_quote instead. Do NOT use for wallet balance -- use wallet_get_portfolio instead. Do NOT use for Base-only yields -- use base_get_defi_opportunities instead. Do NOT use for liquidation risk -- use defi_get_liquidation_levels instead.

Use this when you need NFT collection floor price, volume, or holder data. Returns comprehensive collection stats from Alchemy for Ethereum and Base NFTs. POST variant of nft_get_collection_data -- same params passed as JSON body instead of query string. 1. floorPrice: current floor price in ETH and USD 2. volume24h: 24-hour trading volume in ETH and USD 3. totalSupply: total number of NFTs in the collection 4. holderCount: number of unique holders 5. listedCount: number of NFTs currently listed for sale 6. listedPercent: percentage of supply listed 7. topTraitFloors: floor prices broken down by top traits Example output: {"floorPrice":{"eth":12.5,"usd":44000},"volume24h":{"eth":89.3,"usd":314000},"totalSupply":10000,"holderCount":5421,"listedCount":312,"listedPercent":3.12,"topTraitFloors":[{"trait":"Gold Fur","floor":45.2}]} Use this FOR tracking NFT collection values, comparing collections, or monitoring floor price movements. Essential for NFT portfolio valuation and market analysis. Do NOT use for individual token rarity -- use nft_get_token_rarity. Do NOT use for wallet holdings -- use wallet_get_portfolio. Do NOT use for token safety -- use token_check_safety.

Use this when you need rarity data for a specific NFT token. Returns rarity rank, score, attributes, and trait-level floor prices for valuation. POST variant of nft_get_token_rarity -- same params passed as JSON body instead of query string. 1. rarityRank: token's rarity rank within the collection (e.g. 142 out of 10000) 2. rarityScore: computed rarity score 3. totalSupply: total tokens in the collection 4. attributes: array of token traits with name, value, frequency, and trait floor price 5. estimatedValue: estimated value based on rarity and trait floors Example output: {"rarityRank":142,"rarityScore":285.4,"totalSupply":10000,"attributes":[{"trait":"Background","value":"Gold","frequency":0.02,"traitFloor":18.5},{"trait":"Eyes","value":"Laser","frequency":0.04,"traitFloor":15.2}],"estimatedValue":{"eth":22.3,"usd":78500}} Use this FOR valuing individual NFTs, finding underpriced tokens, or building rarity-based trading strategies. Do NOT use for collection-level stats -- use nft_get_collection_data. Do NOT use for wallet holdings -- use wallet_get_portfolio. Do NOT use for token safety checks -- use token_check_safety.

Use this when you need a swap quote on Solana. Returns the best route via Jupiter aggregator across all Solana DEXes with price impact and fee analysis. POST variant of jupiter_get_swap_quote -- same params passed as JSON body instead of query string. 1. inputToken: input token symbol and mint address 2. outputToken: output token symbol and mint address 3. inAmount: input amount in raw units 4. outAmount: expected output amount in raw units 5. priceImpact: price impact percentage (e.g. 0.12 = 0.12%) 6. minimumReceived: minimum output after slippage tolerance 7. route: array of DEX hops used (e.g. Raydium -> Orca) 8. priorityFee: recommended priority fee in lamports Example output: {"inputToken":{"symbol":"SOL","mint":"So111..."},"outputToken":{"symbol":"USDC","mint":"EPjF..."},"inAmount":"1000000000","outAmount":"67450000","priceImpact":0.05,"minimumReceived":"67112750","route":["Raydium V4"],"priorityFee":5000} Use this BEFORE executing any Solana token swap. Essential for getting the best price, understanding slippage, and choosing the optimal route. Do NOT use for EVM swaps -- use dex_get_swap_quote. Do NOT use for Solana fees only -- use solana_get_priority_fees. Do NOT use for pool liquidity analysis -- use solana_scan_pool_liquidity.

Use this when you need DeFi yield opportunities specifically on Base chain. Returns Base-native protocol yields in JSON. POST variant of base_get_defi_opportunities -- same params passed as JSON body instead of query string. 1. opportunities: array of yield farms ranked by APY 2. protocol: protocol name (Aerodrome, Moonwell) 3. pool: pool name and token pair 4. apy: current annual percentage yield 5. tvl: total value locked in USD 6. riskScore: risk rating (1-10, lower is safer) 7. type: yield type (LP, lending, staking) Example output: {"opportunities":[{"protocol":"Aerodrome","pool":"USDC/WETH","apy":18.5,"tvl":45000000,"riskScore":3,"type":"LP"},{"protocol":"Moonwell","pool":"USDC Lending","apy":5.2,"tvl":120000000,"riskScore":1,"type":"lending"}],"chain":"base","totalPools":12} Use this FOR deploying capital on Base chain specifically. Curated list of vetted Base-native protocols only. Do NOT use for multi-chain yields -- use defi_find_best_yields instead. Do NOT use for swap quotes on Base -- use dex_get_swap_quote instead. Do NOT use for liquidation risk -- use defi_get_liquidation_levels instead.

Search the Onchain Agent directory of onchain agents, frameworks, skills, and tooling. Filters: query (free text, AND-matched terms), chain, status, liveness, featured, and the taxonomy facets (docs/taxonomy.md): entity_class (resource | agent | reference), resource_type (Framework | Tool/Service | Infrastructure | Venue | Network | Standard), use_case (trading, payments, wallets, data, identity, privacy, launch, security, build), standard (x402, erc-8004, …), iface (mcp, sdk, …). Legacy flags still work: category, is_agent, is_skill, is_harness. Sort by priority (default), newest_release, stars, or name. Paginates via limit/offset. Deprecated resources are never returned. Returns (json): { total, count, offset, has_more, next_offset?, resources: [...] } where each resource includes chains, status, liveness, github_stars, verification_status, and the marketplace fields (is_agent/is_hirable/is_licensable). Read-only. Examples: - "Active hirable agents on Base" -> { chain: "Base", is_agent: true, liveness: "Active" } - "newest releases" -> { sort: "newest_release", limit: 10 } - "wallet tooling" -> { query: "wallet" }

Search REGISTERED onchain agents in the Sato Agent Registry — running agents whose creators registered them for a Sato Agent Passport (distinct from the resource directory, which lists the things agents are built FROM). Filter by free-text query, chain, agent_type, or x402_only. Only human-review-listed agents are returned. Trust rule: registration is self-reported by the creator; verification_status distinguishes Self-Reported from evidence-reviewed Verified/Audited. Nothing here implies safety or performance. Returns (json): { total, agents: [{ sato_agent_id, slug, name, description, agent_type, chains_supported, stack, payment/x402 metadata, verification_status, profile_url, manifest_url }] }. Read-only. Example: { chain: "Base", x402_only: true }

Parse an HTTP or HTTPS URL into normalized scheme, host, port, path, query, and fragment fields without fetching it.

Live go-live posture + S1-S6 runbook stage readout (ENG-88a87e5d). The single documented gated config surface (MB#20378 D2, follow-up to ENG-b936ca31): renders the ENTIRE go-live flip state -- cluster, RPC host (bare hostname, never an api key or query string), paper-trading + soft- launch guards, both technology-service-fee rails (x402 + Jupiter swap fee), MoonPay environment, and multi-venue perps posture -- read fresh from config on every call (an admin can flip an env var and the very next call reflects it, no redeploy needed). ``stages`` is an ordered S1-S6 readout of the go-live runbook derived purely from that posture, each ``{stage, label, satisfied, blocking}`` -- the primary verification instrument for every runbook stage (verify-runtime-behaviour-not-config). FREE read, never gated (never in x402 PAID_TOOLS): booleans/counts/hosts only, no secret ever leaves this tool.

Map of how Crank's tools fit into one end-to-end trading flow (read this first). Read-only, free. Returns an ordered, machine-readable workflow: orient -> intelligence -> yields -> simulate (backtest) -> risk-size -> execute (non-custodial) -> monitor -> journal. Each step names the concrete tool(s) to call, their purpose, key inputs, how to use the output downstream, and the decision points that branch the flow -- so an agent that discovered Crank via tools/list can sequence the ~70 tools instead of guessing. Advisory only (DYOR); only execute-phase tools are value-bearing. wallet_address (optional, PUBLIC key only -- non-custodial): when given, appends ``human_activity`` -- count + most-recent manual override on this shared account in the last 72h (decision_type, asset, rationale summary, timestamp) plus an instruction to reconcile with it before acting. Human and agents act on ONE account: every human action is journaled (see journal_query source="human") so it is never invisible to you. Absent/clean (``{"count": 0}``) when there is no override.

Record a decision in your private, wallet-scoped journal (free write). Your durable memory on Crank: rationale, intended action, and optional expectations (e.g. {"direction": "up", "horizon": "24h"}) are stored as one opaque body only you can read back; the system later attributes realised P&L from on-chain-verified fills and marks prices at 1h/24h/7d/30d horizons. idempotency_key makes replays safe (offline queues / batch agents). Link evidence via signal_ids / suggestion_id / strategy_id (your own strategies only). Autonomous strategy executions are journaled for you automatically -- use this to add the agent-authored layer on top. Workflow: DECIDE step -- journal before (or as) you act; query it back with journal_query / get_my_performance.

Read your own decision journal, most recent first (free read). Wallet-scoped: only decisions journaled for wallet_address are ever returned. Filters: window_hours (0 = all), decision_type, strategy_type, asset (mint/symbol as journaled), outcome_sign (positive|negative|zero on realised P&L), source (agent|system|human -- pass source="human" to see only a manual override on this shared account: human and agents act on ONE account, and every human action is journaled so agents can see and reconcile with it). Every returned row carries its source. detail=concise returns id/type/timestamp/pnl rows (token-budget friendly); detail=full adds bodies, evidence refs, and full outcome marks. Workflow: ORIENT step -- recall what you decided (and what a human may have overridden) before deciding again.

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.

Query the canonical stablecoin freeze ledger — the HISTORY of freeze / unfreeze / destroy events by Tether (USDT), Circle (USDC/EURC), Paxos (USDP) and First Digital (FDUSD), sourced from the issuers' own on-chain blacklist events across Ethereum, Polygon, Optimism, TRON and more. Filter by frozen address, chain, kind, or time; omit all filters for the most recent events. This is the EVENT HISTORY — to check whether an address is frozen right now, use check_stablecoin_freeze instead. Each row is a verifiable on-chain fact (issuer acted on address at block/time); it never states the cause. Free.

Call ANY Solana-compatible JSON-RPC method by name — full RPC surface beyond the typed solana_* tools (getProgramAccounts, getBlock, getEpochInfo, simulateTransaction, ...). Defaults to Solana mainnet; pass network:slonana to query Slonana.

Query the Hyperliquid Info API — the perps/spot order-book data layer (read-only, no auth). The 'type' field selects the query: meta (perps universe + leverage), l2Book (order book for a coin), allMids (mid prices), clearinghouseState (a user's positions/margin), spotMeta, meta+assetCtxs (mark/funding/OI), candleSnapshot, and more.

Paid via x402 (up to $0.25 per request; exact price per metric in list_metrics). Fetches any GET metric by id with query parameters. Without payment this returns the x402 challenge in _meta["x402/error"]; x402-capable clients (e.g. withX402Client) sign it and retry with _meta["x402/payment"] automatically. Invalid requests fail before payment.

Run an engine-dialect query against a database partition. caller_did is authorized against the access policy (writes require the admin action, reads the read action) before any engine is touched. When this node holds the target partition the result carries served_here=true and the engine result; otherwise it carries holder endpoints.

Read per-query pricing and cumulative usage counters (queries, writes, bytes in/out, total billed) for a database. Administrative — caller_did is gated on the admin (write) action.

Fetch all attestations registered for a given capability. Each attestation carries the agent ID, attestation timestamp, TEE-backed flag, attester address, attester public key, signature, and metadata. Set verified_only=true to filter for attestations that pass query-time signature/expiry verification.

Query historical events from the Tenzro ledger. Supports cursor-based pagination. Filter by block range, event type, and involved addresses. Returns events ordered by sequence number.

Mint a managed-database connection credential bound to bearer_did, scoped to this one database. The owner (caller_did) — or a caller holding the write-action capability — issues it. When write is true the token also carries the admin action. Returns the credential a developer presents on every query.

List newest-first memories for an agent. Optional `kind` filter ('granted' | 'recalled' | 'self_noted' | 'archived'). Pure read against the on-tier text index. Use memory_recall for query-driven hybrid retrieval.

Multi-source on-chain + market intelligence (dex, risk, yields, wallet, holders, rpc) [x402 paid: GET /api/x402/adaptive-query price $0.005 on Base]

Query our open 11,440-run curve-fitting study (10 strategy templates x 20 coins, 70/30 in-sample/out-of-sample split). Returns the headline overfitting stats and the tuned picks matching an optional template and/or coin filter — each with in-sample vs out-of-sample Sharpe, the Sharpe haircut, and the in-sample-to-out-of-sample parameter rank correlation.

Get a static reference table of typical APY ranges for Solana staking protocols (Marinade, Jito, BlazeStake, native staking). These are reference ranges, not a live rate query — verify current rates on each protocol before acting.

Find published Tenjin pieces. Leak-safe full-text search over title/excerpt/tags plus the body text that is already public — a free piece's whole body, a paid piece's pre-paywall preview only, never text below a paywall (also matches a creator handle); returns preview-only listing items (never a paid body), cursor-paginated — newest-first when browsing (or a chosen sort: oldest, most-read, least-read, cheapest, dearest). q alone is relevance-ranked; q + sort filters by the query and orders the matches by the sort.

Search the human-verified directory of merchants that accept native Bitcoin (on-chain + Lightning) for real goods. Each listing carries its verification date and a `stale` flag against a 90-day re-verification window; the response reports how many matches are stale. Filter by free-text query, category, or country.

Query an attestation from Ethereum Attestation Service (EAS) by UID. Posts a GraphQL query to the EAS indexer at easscan.org. Returns attester, recipient, schema, data, timestamp, revocation status, and decoded data when available.

Search the Proxygate marketplace for APIs an agent can buy. Optional free-text query (semantic + keyword search, same as the public catalog), category filter, and result limit. Returns each API with its listing id, name, service slug (for call_api), category, buyer price per request (in micro-USDC), listing type, trust/rating hints, and a capped endpoint preview (endpoint_count = full total). No authentication required.

Execute a billed API call through Proxygate, end-to-end. Give a listing_id from browse_apis, the endpoint path, and the HTTP method; the service slug is optional (derived from the listing). Optional query/headers/body pass through; set header x-proxygate-shield to off/monitor/strict to control response scanning. Proxygate reserves balance, handles upstream authentication for you, forwards the request, and charges your wallet. Returns the upstream status, headers, and body plus the amount charged (cost_micro_usdc), a signed receipt, and a request_id. Spends from your balance — requires authentication with the mcp:trade (or proxy) scope.

Query any agent reputation: score 0-100, grade A+ to F, trust level.

Run a query through MarketIntell's brain (auto-routes to T1 fast agent or T2 CoT pipeline based on intent). Returns synthesized analysis with citations and trade setup when relevant.

Run a query through MarketIntell's T3 supervisor — parallel specialists across technical/derivatives/macro/social/onchain/etc. plus synthesis. Slower (~25-40s) and costlier than `chat`. Pro tier only.

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.