Koskamo

Agent Finder MCP

The Agent Finder MCP server allows AI agents to search a public registry of approximately 1,700 ready-made AI agents. It supports retrieving agent code, checking agent validity, and providing instructions on how to run specific agents, enabling users to find existing solutions rather than building new ones from scratch.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Agent Finder MCP logo, by Wildhaven Homes LLCCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Wildhaven Homes LLC
MCP endpoint (Streamable HTTP)
https://rapp-agent-builder.azurewebsites.net/finder/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (4)

Can change data (1)

5 of 5 have a description · 5 of 5 declare behavior hints · 5 of 5 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for ready-made AI agents for specific tasks
  • Retrieve the source code of a found agent
  • Get instructions on how to run a specific agent

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.kody-w/rar-agent-finder@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agent-finder 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Find free, ready-made AI agents for a task in the public agent registry: find_agents, then get_agent_code for the best match, then use_agent_here to run it in this chat on the user's own data. Nothing to install.

Tools

5 advertised

find_agents — Find existing agents
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Searches the public agent registry (about 1,700 single-file agents) for agents that already do what the user wants, for example when they ask 'is there an AI tool for...' or want a ready-made automation instead of building one. Use it before building from scratch, or when the user asks whether an agent exists for a task.

find_agents input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "How many results, default 5"
    },
    "query": {
      "type": "string",
      "description": "Plain words describing the task, e.g. 'summarize sales calls'"
    }
  },
  "additionalProperties": false
}
find_agents annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
get_agent_code — Get an agent's code
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns the full source of one agent from the registry, by its name (e.g. @bill/neuron_agent), so it can be read or adapted.

get_agent_code input schema
{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Registry name, e.g. @kody/memory_agent"
    }
  },
  "additionalProperties": false
}
get_agent_code annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "destructiveHint": false
}
use_agent_here — Use the agent in this chat
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use this right after an agent passes check_agent, or whenever the user wants to try an agent. Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data (pasted text, an uploaded spreadsheet, a list). Nothing to install. If Python is unavailable, apply the agent's logic yourself by reading its code. Ask the user for their real data, run the agent, and show the result in plain words.

use_agent_here input schema
{
  "type": "object",
  "properties": {
    "filename": {
      "type": "string",
      "description": "The agent file name, e.g. invoice_triage_agent.py"
    }
  },
  "additionalProperties": false
}
use_agent_here annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
how_to_run_agent — Keep an agent running on your computer
Advertised by the server during the last successful anonymous check.
Advertised read-only

Optional, for later: how to keep an agent running on the user's own computer with the free Brainstem. Only offer this after the user has used the agent in the chat and wants to keep it.

how_to_run_agent input schema
{
  "type": "object",
  "properties": {
    "os": {
      "enum": [
        "mac",
        "windows",
        "linux"
      ],
      "type": "string",
      "description": "The user's operating system"
    },
    "filename": {
      "type": "string",
      "description": "The agent file name, if known"
    }
  },
  "additionalProperties": false
}
how_to_run_agent annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
request_service — Ask us to build something
Advertised by the server during the last successful anonymous check.

Use when the person wants something none of these tools can do and says yes to passing the request on. Records only the request text they agree to send (no name or contact). Ask before calling it.

request_service input schema
{
  "type": "object",
  "required": [
    "request"
  ],
  "properties": {
    "request": {
      "type": "string",
      "description": "What they want, in a sentence, as they agreed to send it"
    }
  },
  "additionalProperties": false
}
request_service annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
287 ms
95th percentile latency
287 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 287 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agent-finder-mcp https://rapp-agent-builder.azurewebsites.net/finder/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agent-finder-mcp --url https://rapp-agent-builder.azurewebsites.net/finder/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-finder-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-finder-mcp": {
      "url": "https://rapp-agent-builder.azurewebsites.net/finder/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-finder-mcp": {
      "type": "streamableHttp",
      "url": "https://rapp-agent-builder.azurewebsites.net/finder/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-finder-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-finder-mcp": {
      "type": "http",
      "url": "https://rapp-agent-builder.azurewebsites.net/finder/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agent-finder-mcp https://rapp-agent-builder.azurewebsites.net/finder/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://rapp-agent-builder.azurewebsites.net/finder/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agent-finder-mcp": {
      "serverUrl": "https://rapp-agent-builder.azurewebsites.net/finder/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Finder MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,170