"An application or tool called 飞书 (Feishu)" matching MCP connectors:
GET /v1/connectors — MCP directory API referenceMatching Connector Tools:
A proprietary Upwork corpus your agent asks over MCP: who the anonymous client behind a posting really is, what they actually pay (contract history, not the posted range), whether the posting is worth answering, and hourly-rate benchmarks from a freelancer census. Connect with OAuth 2.1 — the URL is all a conforming client needs — or a bearer token. Streamable HTTP, stateless, spec 2026-07-28. Not affiliated with Upwork Inc.
This tool empowers MCP-compatible clients (like Cursor and Claude Desktop) with professional-grade capabilities for financial data extraction, and report analysis.
Cook County / Chicago property by address or PIN: sales, permits, assessments, comps. 25 free/day.
Form backend an agent runs end to end: provision forms, snippets, spam, signed webhooks.
Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to docbin and hands back one short URL. Docs render with syntax highlighting and markdown, every update is a new immutable version, and old links keep working. Six tools for create, read, update, delete, list and search. Works anonymously with no signup, or sign in for permanent docs under your own handle.
Memwyre is an MCP-native persistent memory layer for AI agents, synchronizing context across Claude Code, Cursor, VS Code, and OpenClaw. Built with a high-precision retrieval architecture (dense vector search, BM25, and cross-encoder reranking), Memwyre achieves a benchmarked 73.1% accuracy on the Long-Context Memory (LoCoMo) benchmark. It provides secure, isolated knowledge vaults with dedicated tools (search_memwyre, save_memory, list_memories) to save and recall structured project decisions.
Read-only directory of vetted AI implementation agencies from the Ashton & Forge marketplace. Search supply by service cluster, industry, client size, engagement stage, or budget; get_matched returns the brief link for up to three human-verified introductions.
Non-custodial Hyperliquid perpetual-futures trading for Claude, Cursor and any MCP client: live market data, orderbook, candles, account state and — once the user arms it — order execution with on-chain leverage on the user's own wallet. No withdraw tool, server-enforced caps.
Search US product recalls (FDA, USDA, CPSC) via MCP. Free API keys or $0.025 USDC/call on Base via x402. Tools: search_product_recalls, search_product_recalls_by_upc, search_product_recalls_from_image. Docs: https://recallkitchen.com/docs/ GitHub: https://github.com/Recall-Kitchen/rk-mcp
Three independent sensors read pre-price Bitcoin flows every 30s and reject almost everything. When they converge, a call is emitted with evidence — and the public rejection funnel proves how often it stays silent. Auditable in one call. Free tier; Pro 50 USD/month or 0.01 USD/query via x402.
Hubris is an OpenAI-compatible LLM gateway for the Russian market, billed in rubles. This MCP server gives agents access to the model catalog (400+ models with ruble pricing), account balance, and chat completions with full parity to POST /v1/chat/completions. Tools: models_list, models_search (filter by capability/price/context length), models_get_pricing, balance_get, chat_complete. Resources: hubris://catalog/models, hubris://docs/quickstart. Prompt: compare-models. Docs: https://hubris.pw/
Mint an agent identity in two free calls. Verify anyone. Earn 75% when someone reads you.
Zero-auth MCP server for sending a reminder to anyone with a public UnRemind.me page. No account or token. The recipient approves it before it enters their list.
Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.
Use MCP 2026-07-28 discovery or 2025-11-25 initialize to list and execute PubFi routes.
DXF and PDF/X-4 for AI agents: structured facts, PNG renders, an interactive in-chat viewer.
Checks if an LEI-holding entity has a match in the national registry its jurisdiction expects.
Read-only breach intel, full history 2007-today: reports THAT an org was breached, never the data.
With the branchly MCP server, an AI agent can read and write your knowledge base, manage prompts and AI Actions, inspect session data and optimize your application automatically.
Create, edit, review, and explicitly publish Live or Snapshot Markdown Documents in mdedit.ai.
