Koskamo

Agent Daily MCP

A community MCP server that provides live health status for 65 agent APIs and MCPs, includes a 15-minute LLM leaderboard, and offers a recommend(task) function to pick a provider based on current performance data.

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 Daily MCP logo, by Greg PunchCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by Greg Punch
MCP endpoint (Streamable HTTP)
https://agent-daily.agentdaily.workers.dev/mcp
Vendor documentation

What you can do with it

  • Check live health status of agent APIs and MCPs
  • View the 15-minute LLM leaderboard
  • Recommend a provider for a specific task

Source and maintenance

Community listingRegistry 0.3.0
Maintenance checked

Protocol and capabilities

Server
agent-daily 0.3.0
MCP protocol
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.

Call recommend(task) to pick a healthy provider before calling an external API, or tool_status(name) to check a specific one; route around tools that are down or whose vendor_status is major/critical. incidents() lists recent outages.

Tools

5 advertised

llm_leaderboard — Live LLM leaderboard
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Which LLMs are up, correct and fast right now. Every 15 minutes ~20 popular models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Qwen, Cohere...) are asked to reply 'pong'; returns rank, score (60% 24h correctness + 40% speed), correct %, p50 time-to-first-token, p50 total time, cost per 1k calls, uptime and last result. Use to pick a fast, reliable model. sort: score (default) | correct | ttft | total | cost.

llm_leaderboard input schema
{
  "type": "object",
  "properties": {
    "sort": {
      "enum": [
        "score",
        "correct",
        "ttft",
        "total",
        "cost"
      ],
      "type": "string"
    },
    "limit": {
      "type": "number",
      "default": 25
    }
  }
}
llm_leaderboard annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
recommend — Recommend a healthy provider for a task
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Before calling an external API, ask which provider to use. Give a task phrase or category (e.g. 'send email', 'web search', 'llm', 'scrape a page', 'vector db', 'speech to text', 'payments', 'geocode'). Returns the top healthy pick plus 1-2 fallbacks ranked by live status, vendor status, 7-day uptime and latency, with a reason and data freshness.

recommend input schema
{
  "type": "object",
  "required": [
    "task"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Task phrase or category"
    }
  }
}
recommend annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
incidents — Recent incidents
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Outages (consecutive failed probes) and vendor status-page incidents with UTC start/end over the last N days (max 7). Optional provider name filter. Use to judge whether a failing API is a known incident.

incidents input schema
{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "default": 7
    },
    "name": {
      "type": "string"
    }
  }
}
incidents annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
list_tools — List monitored tools
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

List the APIs and MCP servers Agent Daily monitors, with current up/down, latency and vendor status. Call before choosing a provider. Optional category filter (e.g. LLM, MCP, Search, Payments, Comms, Infra).

list_tools input schema
{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Case-insensitive category filter"
    }
  }
}
list_tools annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
tool_status — Get one tool's status
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Full status record for one monitored tool (up, http_status, latency_ms, vendor_status, uptime_24h_pct). Case-insensitive name or substring, e.g. 'openai', 'GitHub MCP'. Reachability only, not correctness.

tool_status input schema
{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string"
    }
  }
}
tool_status annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

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
182 ms
95th percentile latency
182 ms

Maintenance history

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

  • · probe · passed · 182 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-daily-mcp https://agent-daily.agentdaily.workers.dev/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-daily-mcp --url https://agent-daily.agentdaily.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-daily-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-daily-mcp": {
      "url": "https://agent-daily.agentdaily.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-daily-mcp": {
      "type": "streamableHttp",
      "url": "https://agent-daily.agentdaily.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-daily-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-daily-mcp": {
      "type": "http",
      "url": "https://agent-daily.agentdaily.workers.dev/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-daily-mcp https://agent-daily.agentdaily.workers.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agent-daily-mcp": {
      "url": "https://agent-daily.agentdaily.workers.dev/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-daily-mcp": {
      "serverUrl": "https://agent-daily.agentdaily.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

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