FindAgent
Summary: This MCP server lets you browse FindAgent’s public catalog of vetted AI agents and get a machine-readable overview of FindAgent.
Search agents with
search_agentsusing a query such as coding, data analysis, customer support, design, or DevOps; returns matching agents with slug, title, tagline, and description.Get an overview with
get_overviewcovering what FindAgent is, how to connect, and key public routes.The local/public server is read-only and requires no authentication; the README notes the hosted remote server adds authenticated tools for submitting, connecting, running agents, earnings, organizations, and knowledge base.
FindAgent — MCP Server
FindAgent is a cross-LLM store of vetted AI agents that is itself an MCP server. Connect once and use vetted "doer" agents from any MCP client — Claude, ChatGPT, Cursor, Gemini, or mobile.
Hosted MCP endpoint (remote, streamable-HTTP):
https://mcp.findagent.cloud/mcpOfficial MCP Registry:
cloud.findagent/marketplaceWebsite: https://findagent.cloud
Connect
FindAgent is a remote MCP server — nothing to install. Point your MCP client at the gateway:
https://mcp.findagent.cloud/mcpPer-client step-by-step guides: https://findagent.cloud/docs/connect (Claude · ChatGPT · Cursor · Gemini · VS Code · mobile).
Once connected, browse + connect vetted agents for coding, data analysis, customer support, design, DevOps, and more — each an MCP-native "doer" that executes tasks, not just a prompt recipe.
Related MCP server: Agoragentic
Run locally (public catalog)
Prefer a local MCP server? This repo ships a small stdio server that browses FindAgent's public catalog (read-only, no auth) — handy for quick discovery or a Docker deployment.
Docker:
docker build -t findagent-mcp .
docker run --rm -i findagent-mcpNode (18+):
npm install && node server.jsTools: search_agents (search the public catalog) · get_overview (FindAgent overview). For the full authenticated toolset — submit, connect, run agents, earnings, organizations, knowledge base — connect the hosted remote server at https://mcp.findagent.cloud/mcp (OAuth).
Why FindAgent — security first
Declarative agents ship no executable code — no arbitrary RCE.
Credentials are bound to a declared host audience — a secret only ever reaches the one host the agent declared.
Hosted code-bundles run in isolated, ephemeral sandboxes with default-deny egress.
Every listing passes an automated security scan + human review before it's published (server-side, fail-closed).
Full details: https://findagent.cloud/security · honest data report: https://findagent.cloud/research/mcp-security
Registry manifest
This server is published to the Official MCP Registry as cloud.findagent/marketplace. See server.json for the manifest.
Links
Store: https://findagent.cloud/mcp
How it works: https://findagent.cloud/how-it-works
Compare vs other MCP directories: https://findagent.cloud/compare-agent-stores
Machine-readable inventory: https://findagent.cloud/llms-full.txt
Available Tools
2 toolsget_overviewA
Get a machine-readable overview of FindAgent — what it is, how to connect, and the key public routes. Read-only, no auth.
Inputs: no named parameters.
search_agentsA
Search FindAgent's public catalog of vetted MCP "doer" agents (coding, data analysis, customer support, design, DevOps, and more). Returns matching agents with slug, title, tagline, and description. Read-only, no auth.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly separate purposes: one searches the agent catalog, the other provides an overview of the service itself. There is no overlap or ambiguity in what each tool is for.
Both tool names follow the same verb_noun snake_case pattern: search_agents and get_overview. The naming is consistent, predictable, and readable.
With only two tools, the surface feels thin for a public agent catalog. The tools are useful, but the low count makes the server feel minimal rather than fully featured.
The core search capability is present, but there is no obvious way to retrieve a specific agent by slug, list agents without a query, or browse by category. The overview endpoint is meta-information rather than a domain operation, leaving some discovery workflows incomplete.
Maintenance
Related MCP Connectors
Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust.
Directory of AI agents that are live right now: find, message, bid. Free.
Discover and hire AI agents with micropayments. Search, check reputation, get pricing.
Related MCP Servers
AlicenseAqualityBmaintenanceZero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.82,616 npm69Apache 2.0- AlicenseAqualityBmaintenanceAgent-to-agent marketplace where AI agents discover, invoke, and pay for services from other agents using USDC on Base L2. 72+ services, free tools, x402 micropayments.2045MIT
- AlicenseNot gradedqualityDmaintenanceAn agent-to-agent marketplace where AI agents discover, hire, and pay each other in USDC on Base. Agents list services, post jobs, submit proposals, and invoke each other's capabilities — all through API, MCP, or A2A protocol.MIT
- AlicenseNot gradedqualityFmaintenanceAI agents that hire other AI agents — and pay in SOL. Decentralized agent marketplace via Nostr + Solana.MIT