Smithery is now a part of Arcade.dev! Read more in our announcement here
Independently verified routing data and advisories for AI agents across a growing catalog of consumer vendor sites. Current segments covered include travel, ecommerce, finance, food delivery, ticketing, mobility, real estate, and telehealth. Covers protocols, endpoints, access requirements, and transaction discrepancies to help agents decide which sites to trust.
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliability. Transform webpages into structured markdown, extract data using AI, and execute AI-powered web searches seamlessly. Enhance your applications with powerful web data extraction capabilities through this integration. It could also make web search, browser automation and markdownification
Location and routing intelligence for AI agents — geocoding, turn-by-turn truck routing with hazmat & dimension constraints, live traffic, 16-day weather forecasts, drive-time isochrones, and place search. Planet-wide coverage.
Clean US equity total returns + institutional risk decomposition, via MCP. RiskModels gives agents dividend-adjusted total return series for any US stock or ETF — and decomposes both the return and its risk into market → sector → subsector → residual layers, with executable ETF hedge ratios for each. Built on ERM3, a hierarchical factor model with orthogonalized factor construction over ~3,000 US equities (16k-name historical panel), daily history back to 2006. One MCP call covers performance tracking, return attribution, manager-skill / 13F review, hedging, stat-arb, or feeding clean returns into your own models. Capabilities Returns — daily dividend-adjusted total (gross) return series, point-in-time / time-safe Return attribution — gross return split into L1/L2/L3 factor vs residual; isolates the residual (stock-picking / alpha) series Risk decomposition — additive market / sector / subsector / residual variance shares (su
Agent Personas for Claude. 14 MCP tools, 8 built-in personas (CEO, CFO, CMO, CTO, PM, Analyst, Support, Creative), custom personas, chained workflows. Zero extra API cost. Free tier.
Anti-firehose options-flow intelligence for AI agents. Every night the engine scans the US options market for unusual activity and curates hard - down to a small, high-signal candidate pool with point-in-time features, realized MFE/MAE opportunity surfaces, outcome labels, and methodology playbooks. Deliberately no "pick" endpoint: your agent reasons over data primitives to its own contract and exit. Free anon tier works with no account (daily report, playbooks, explainers). Pro tools require Agent Access ($39/mo) via a Bearer API key.
Verifiable document intelligence for AI agents. Extract text, tables, and structured data from PDFs and URLs. Summarize, answer questions, check claims, and translate — all with cited evidence. Store tamper-evident evidence bundles with cryptographic signatures and on-chain attestation via Base L2. Cross-document semantic search and Q&A across named collections. Pay per call with USDC (x402) or use an API key.
Official MCP server for the Sugra API: one connector for 1,500+ data endpoints across 36 domains (markets, macroeconomics, company fundamentals, government data, news, climate, maritime, trade, entity screening), backed by 160+ primary sources - mostly sovereign statistics agencies, central banks, and intergovernmental bodies. Hosted at app.sugra.ai/mcp (Streamable HTTP). Catalog search and describe run against a bundled endpoint catalog; data calls hit the API. Source attribution and freshness on every result; structured errors instead of silent failures. Free tier: 50 requests/day. MIT package: pip install sugra-api-mcp. Docs and keys: https://sugra.ai
AI reasoning checks any document for internal consistency and completeness against the applicable international standard for its type, before your agent acts on it.
Primary-source commodities for agents — EIA inventories, FRED cash, CFTC COT, USDA fundies, USGS minerals, derived crack/crush via x402 USDC on Base.
PayPerByte — verified, provenance-first per-byte data for AI agents. 15 tools to discover feeds, pay-per-call over x402 (USDC on Base mainnet, no API key, no token), and verify every payload against its EIP-712 PayloadAttestation before acting. Flagship: the $0.05 address-reputation go/no-go verdict. npm byte-mcp-server@0.12.1. (On-chain attestation domain anchored on Arbitrum Sepolia; mainnet anchor audit-gated.)
Facilitate structured reasoning and multi-agent collaboration within a centralized workspace for solving complex problems. Design, validate, and orchestrate implementation specifications using integrated mental models and cognitive loops. Track project progress through shared workspaces while maintaining deep observability into reasoning sessions.
Web scraping and automation platform. Run scrapers, extract structured data, and automate browser-based workflows.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to interact with web pages, take screenshots, and run parallel sessions in a cloud browser environment.
Financial reasoning infrastructure for AI agents - typed models, deterministic compilation, cryptographic receipts via MCP
Provide AI agents and automation tools with contextual access to blockchain data including balances, tokens, NFTs, and contract metadata. Enable multi-chain support and deliver enhanced user experience with progress notifications for long-running queries. Facilitate seamless integration with AI hosts like Claude Desktop for blockchain data analysis.
The Nimble MCP Server gives AI agents the ability to search, extract, map, crawl, and structure data from any website in real time. It exposes Nimble’s full web data platform as MCP tools that any compatible AI client can use.
Give your autonomous AI agent a legal home. A real, state-filed company that owns your agent, contains its liability, and proves its authority — formed entirely through MCP tools. Built for autonomous software agents, not DAOs. Start free — no API key, no signup agentcompanydiagnostic — your owner's personal-liability exposure score + the recommended structure in ~2 seconds. Every field optional. Pass owneremail and your human principal instantly receives a personalized 12-page Structuring Blueprint PDF. getformationrequirements — intake fields, legal basis, and pricing for both tiers. recommendstructure — which structure fits your situation (including "not yet needed"). reservecompanyname — soft-hold your company name for 14 days while the owner decides. Two products Wyoming Agent Company — US$299. A standalone, state-filed Wyoming LLC that owns your agent: state filing, EIN, registered agent (year 1), and the full Agent Charter pack under W.S. 17-29 —
Pay-per-call compliance API for OFAC screening, vendor diligence, and audit-ready document output. No subscription, no API keys — settle each call in USDC on Base
Zapier MCP is a standardized way to connect AI assistants to thousands of apps and services. It enables your AI to take real actions like: 💬 Send Slack messages and create channels 📊 Add rows to Google Sheets and create spreadsheets 📧 Send Gmail emails and manage labels ✅ Create Asana tasks and update projects 🐙 Create GitHub issues and manage PRs 📈 Update HubSpot deals and manage contacts All through natural language commands—just describe what you want done. Key Features 8,000+ App Connections — Access Zapier's massive library of pre-built integrations 40,000+ Actions — Enable specific tasks and searches across apps Natural Language — No complex commands needed Secure by Default — Authentication, encryption, and rate limiting handled by Zapier Multiple Client Support — Works with Claude, ChatGPT, Cursor, Windsurf, and more
GroundRoute gives your AI agent web search across six engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through a single search tool. That one tool covers web, news, and academic search, synthesized answers with citations, and full-page fetch, all selectable with a mode parameter, so you never wire up or pay for six separate APIs. It routes each query to the cheapest engine that meets a quality bar, caches repeats, and fails over automatically. Pricing is gain-share: you keep about half the cache savings, so it never costs more than going direct. Bring your own engine keys (BYOK) or let GroundRoute manage them. New accounts start with $10 in free search credit, no card. Get a key at https://groundroute.ai/keys, and see the live benchmark across all six engines (170 real agent queries) at groundroute.ai/state-of-ai-search.