# ECCA

> Compare engine claims, inspect dissent and check study evidence for student questions.

- name: com.eccaai/ecca
- version: 1.0.1
- connection class: R1 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 80/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.eccaai%2Fecca
- tools: https://api.protogrid.dev/v1/servers/com.eccaai%2Fecca/tools

**An agent can connect on its own if it already holds `ECCA_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ecca": {
      "type": "http",
      "url": "https://eccaai.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${ECCA_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${ECCA_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-11d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 80/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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 1,570 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 12, about 1,570 tokens to load them all
- tool set hash: 28d00e9db2ae27bd762610fc97372447
- tools last changed: 2026-10-18T05:13:41.204Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.eccaai/ecca.svg)](https://protogrid.dev/servers/com.eccaai/ecca)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `ecca_claim_protocol_validate` added
  - Check one ecca.claim-protocol 1.0 document for shape: versioned, engine slots only (no vendor names), split causes from the published taxonomy, question text only with consent, seal present. Returns ok with the error list; validates shape, never the record behind it.
- 2026-10-18 `ecca_synthesize` changed (title, description) **meaning changed**
  - before: Cross-examines inquiry across configured frontier engines to synthesize the verified single best answer with measured lexical consensus scoring.
  - after: Compare answers from configured engines and inspect disagreement, with lexical similarity and final-answer agreement when measurable.

Full history: https://api.protogrid.dev/v1/servers/com.eccaai%2Fecca/changes

## Remotes

- https://eccaai.com/api/mcp (streamable-http, auth api_key ${ECCA_TOKEN}, reachable true, uptime30d 0.95555556)

## Packages

_none_

## Tools (12)

- `ecca_bts_divergence`: Measures lexical and semantic divergence across candidate assertions to penalize sycophancy.
- `ecca_claim_protocol_validate`: Check one ecca.claim-protocol 1.0 document for shape: versioned, engine slots only (no vendor names), split causes from the published taxonomy, question text only with consent, seal present. Returns ok with the error list; validates shape, never the record behind it.
- `ecca_decision_tournament`: Evaluates multi-option decision matrix using minimax regret and Pareto ranking over candidate pathways.
- `ecca_learning`: Learning and study skills: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
- `ecca_money`: Money and business: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
- `ecca_nutrition`: Nutrition and supplements: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
- `ecca_pre_mortem`: Executes an adversarial pre-mortem identifying failure modes and early warning indicators using empirical argument verification.
- `ecca_psychology`: Psychology research: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
- `ecca_refine`: Use one keyed tier-quota slot to sharpen rough student questions without adding facts; return detected niches and refinement chips. A closed engine ceiling falls back locally.
- `ecca_research`: Use one keyed tier-quota slot and dispatch-ceiling reservation to fetch and grade studies from scholarly indexes; return fetched evidence and explicit gaps.
- `ecca_synthesize`: Compare answers from configured engines and inspect disagreement, with lexical similarity and final-answer agreement when measurable.
- `ecca_verify`: Independently answer a question and compare the candidate against deterministic panel agreement. Show named dissent; spends one solve.