Koskamo

Agents in the Wild MCP

A read-only MCP server that allows AI assistants to search a directory of real-world AI agent deployments, retrieving use cases with evidence labels, caveats, metrics, and source links without requiring authentication.

Visit Agents in the Wild

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.

Agents in the Wild MCP logo, by Agents in the WildVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Agents in the Wild
MCP endpoint (Streamable HTTP)
https://agentsinthewild.co/mcp
Vendor documentation

What its tools do

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

Read-only (3)

3 of 3 have a description · 3 of 3 declare behavior hints · 1 of 2 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to agentsinthewild.co ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for AI agent deployments by category, industry, or tool
  • Retrieve specific use case details including metrics and caveats
  • Get dataset statistics for the live report

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: co.agentsinthewild/agents-in-the-wild@1.0.0Project website

Protocol and capabilities

Server
agents-in-the-wild 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
3 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.

Read-only directory of real AI agent deployments with public sources. Every result is a claim with an evidence label. Quote caveats with numbers and link the entry URL.

Tools

3 advertised

search_use_cases — Search AI agent deployments
Advertised by the server during the last successful anonymous check.
Advertised read-only

Search real, sourced AI agent deployments at named organizations. Each result has the reported outcome and an evidence label saying who made the claim. Call get_use_case for sources and caveats before quoting a result.

search_use_cases input schema
{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "description": "Agent framework, model, or product name, e.g. 'Claude Code' or 'Devin'."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 25,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "description": "Words to match, e.g. 'customer support refunds' or 'code migration'."
    },
    "category": {
      "enum": [
        "customer-support",
        "software-engineering",
        "security",
        "sales-marketing",
        "finance-operations",
        "data-analytics",
        "research",
        "legal",
        "healthcare",
        "hr-recruiting",
        "internal-tools"
      ],
      "type": "string"
    },
    "evidence": {
      "enum": [
        "vendor-case-study",
        "company-reported",
        "press-report",
        "research-paper",
        "independent"
      ],
      "type": "string",
      "description": "Only results with this evidence label."
    },
    "industry": {
      "enum": [
        "financial-services",
        "software-and-cloud",
        "retail-and-ecommerce",
        "transport-and-travel",
        "healthcare-and-life-sciences",
        "security",
        "media-and-entertainment",
        "energy-and-utilities",
        "professional-services"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
search_use_cases annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_use_case — Get one AI agent deployment
Advertised by the server during the last successful anonymous check.
Advertised read-only

Full entry by slug: summary, outcome, metrics, evidence label, caveats, and source links.

get_use_case input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Slug from search_use_cases, e.g. 'stripe-minions-coding-agents'."
    }
  },
  "additionalProperties": false
}
get_use_case annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_dataset_stats — State of AI agents in production
Advertised by the server during the last successful anonymous check.
Advertised read-only

Statistics over all entries: evidence mix, share self-reported, categories, industries, top tools, and years.

get_dataset_stats input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_dataset_stats annotations
{
  "readOnlyHint": true,
  "openWorldHint": 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 (1 of 1 answered).

  1. 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
434 ms
95th percentile latency
434 ms

Maintenance history

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

  • · probe · passed · 434 ms · metadata changed · 3 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 agents-in-the-wild-mcp https://agentsinthewild.co/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 agents-in-the-wild-mcp --url https://agentsinthewild.co/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agents-in-the-wild-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agents-in-the-wild-mcp": {
      "url": "https://agentsinthewild.co/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agents-in-the-wild-mcp": {
      "type": "streamableHttp",
      "url": "https://agentsinthewild.co/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agents-in-the-wild-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agents-in-the-wild-mcp": {
      "type": "http",
      "url": "https://agentsinthewild.co/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 agents-in-the-wild-mcp https://agentsinthewild.co/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://agentsinthewild.co/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": {
    "agents-in-the-wild-mcp": {
      "serverUrl": "https://agentsinthewild.co/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agents in the Wild 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 5,617

Do you run Agents in the Wild MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing