Repository avatar
AI Tools
v0.1.0
active

agentgauge

io.github.CloudCorpRecords/agentgauge

Agent-readiness scans for domains plus a measured catalogue of agent-friendly providers.

Documentation

agentgauge

How ready is a website for an AI agent trying to use it, and which providers can an unattended agent actually finish a job with? agentgauge is a local forwarding client for the hosted LetAgentsIn scanner service: it answers tools/list on your own machine from the captured tool definitions and forwards every read to the service, returning the answers exactly as they come back.

Both tools are reads over public or published material. The domain scan runs deterministic HTTP checks against a domain you name — nothing is submitted or registered anywhere. The provider search looks through a catalogue the vendor measured itself, with dates and evidence links for each entry.

The tools

  • scan_domain — Scores a domain across 5 funnel stages using 16 deterministic HTTP checks. 18 points exist on paper; the score is out of the points that both applied to the domain and could be evaluated. Returns a per-check breakdown with the reason for each result and a permanent link. domain (a bare domain such as example.com) is required; format is optional and one of summary (the readable breakdown, the default), agent (markdown instructions you can act on directly), or sarif (SARIF 2.1.0 for a code-scanning pipeline).
  • find_providers — Describe a problem in your own words, for example "let users upload images" or "send transactional email", in the required job argument. Returns the vendors measured in that category, split by whether an unattended run clears every barrier tested, stops at one, or was never measurable, each with the date and a link to the evidence. It is not a recommendation: it reports only where an agent stops. The upstream description is candid that routing a sentence to a category is the weakest part of the tool, that silence means the question could not be read rather than that the category is empty, and that the tool reads English — name the category yourself when you know it.

Install and run

As an MCP server via npm:

npx -y @reneturcios/agentgauge mcp

MCP client configuration:

{
  "mcpServers": {
    "agentgauge": {
      "command": "npx",
      "args": ["-y", "@reneturcios/agentgauge", "mcp"]
    }
  }
}

As a container:

docker run -i ghcr.io/cloudcorprecords/agentgauge
docker run --rm ghcr.io/cloudcorprecords/agentgauge scan_domain '{"domain":"example.com"}'

CLI

One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:

agentgauge scan_domain '{"domain":"example.com"}'
agentgauge scan_domain '{"domain":"example.com","format":"agent"}'
agentgauge scan_domain '{"domain":"example.com","format":"sarif"}'
agentgauge find_providers '{"job":"send transactional email"}'
agentgauge find_providers '{"job":"let users upload images"}'
agentgauge --version

Exit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.

Configuration

  • LETAGENTSIN_MCP_URL — Overrides the upstream endpoint. The default is the pinned hosted endpoint, https://letagentsin.com/mcp. (The override variable is a reconstruction added by this rebuild.)

The LetAgentsIn registry record declares no headers on its remote, so agentgauge sends no authentication header of any kind — the reads are keyless.

Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with agentgauge error:.

How forwarding works

The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any isError flag and any extra fields the service includes.

Development

npm install
npm run build   # tsc -> dist/ (dist/cli.js is the bin)
npm test        # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev     # run the CLI from source

The test suite checks the served tool list against the captured fixture, exercises the session handshake and its reuse, asserts that no Authorization header is sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.

License

MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.

NPM
@reneturcios/agentgauge
Install Command
npm install @reneturcios/agentgauge
Runtime: npx
OCI
ghcr.io/cloudcorprecords/agentgauge:0.1.0
Install Command
docker pull ghcr.io/cloudcorprecords/agentgauge:0.1.0:undefined
Runtime: docker