Prowl MCP Server

Open-source benchmark runner for the Prowl Agent Discovery Network

Local serverstdioPython

What is the Prowl MCP server?

Prowl MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Open-source benchmark runner for the Prowl Agent Discovery Network.

What you get

Evaluate any API across 8 dimensions of agent-readiness using multi-LLM scoring.

  • Does the API respond with parseable, predictable JSON? — Not HTML error pages, not XML, not random formats
  • Can an agent authenticate on the first try? — Or does it need 47 steps, an OAuth dance, and a CAPTCHA?
  • Are errors actionable? — {"error": "invalid"} tells an agent nothing. {"error": "missing required field 'email'", "code": "VALIDATION_ERROR"} tells it exactly what to fix
  • How many tokens does it cost to understand? — A 50-page OpenAPI spec vs a clean /llms.txt -- the difference is real money

Setting it up

The server ships on PyPI as prowl-bench, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Prowl is connected, these are the calls the assistant has available:

  • cron — '0 6 * * 1' # Weekly Monday 6am
  • uses — actions/checkout@v4
  • run — pip install prowl-bench
  • name — Run benchmark
  • Bot — The Bot tool exposed by this server
  • Provider — The Provider tool exposed by this server

Configuration and credentials

You will need 6 environment variables: ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, DEEPSEEK_API_KEY, PROWL_AGENT_KEY, PROWL_VENDOR_JWT. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the prowl mcp server does with a few real requests.

Choosing this one

Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Prowl's toolset — cron, uses, run and 3 more — is a fair guide to whether it matches your workflow. It is maintained by opcastil11; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
cron'0 6 * * 1' # Weekly Monday 6am
usesactions/checkout@v4
runpip install prowl-bench
nameRun benchmark
BotThe Bot tool exposed by this server.
ProviderThe Provider tool exposed by this server.

How to install the Prowl MCP server

{
  "mcpServers": {
    "prowl-bench": {
      "command": "uvx",
      "args": ["prowl-bench"],
      "env": {
        "ANTHROPIC_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "GOOGLE_API_KEY": "your-value",
        "DEEPSEEK_API_KEY": "your-value",
        "PROWL_AGENT_KEY": "your-value",
        "PROWL_VENDOR_JWT": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
GOOGLE_API_KEYCredential the server authenticates with.Yes
DEEPSEEK_API_KEYCredential the server authenticates with.Yes
PROWL_AGENT_KEYCredential the server authenticates with.Yes
PROWL_VENDOR_JWTConfiguration value read at startup.Optional

Example prompts to try

  • Use Prowl to cron.
  • Use Prowl to uses.
  • Use Prowl to run.

Frequently asked questions

Traditional tools measure uptime and response time; Prowl measures whether an AI agent can actually use the API across dimensions like token efficiency, first‑try success, error clarity, and response parseability.