# EvalGate

> Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

- name: com.evalgate/evalgate
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 94/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.evalgate%2Fevalgate
- tools: https://api.protogrid.dev/v1/servers/com.evalgate%2Fevalgate/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-3d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,896 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 1,896 tokens to load them all
- tool set hash: 0dd997bffe96e67b6456298199cde2bb
- badge: [![protogrid quality](https://protogrid.dev/badge/com.evalgate/evalgate.svg)](https://protogrid.dev/servers/com.evalgate/evalgate)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://www.evalgate.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (12)

- `baseline_lineage`: Show the published baseline anchor and its evidence lineage.
- `connections_catalog`: Inspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.
- `connections_graph`: Read canonical connection references and currently visible exact resource revisions. No source access grant or execution.
- `connections_list`: List current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.
- `connections_roots`: Page independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.
- `connector_health`: Show the latest connector-readiness reports for the organization.
- `docs_search`: Search the published OpenAPI operation catalog for relevant help.
- `evaluations_list`: List evaluations with a stable cursor for the organization.
- `project_inspect`: Inspect the evaluations and project keys available in the authenticated organization.
- `project_plan`: Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.
- `run_explain`: Explain a run using its status, failed-case metadata, and evidence-lineage summary.
- `runs_list`: List evaluation runs with stable cursors and regression signals.