ECCA
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Compare engine claims, inspect dissent and check study evidence for student questions.
| Author | com.eccaai |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2725 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"ECCA": {
"url": "https://eccaai.com/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (12)
ecca_synthesizeCompare answers from configured engines and inspect disagreement, with lexical similarity and final-answer agreement when measurable.
Parameters:
query(required) — string — The core inquiry, hypothesis, or decision challenge to synthesize.depth— string — intuitive and fast route to one engine; executive, pioneer and deep route a multi-engine dispatch (free callers: two engines first, expanding on measured divergence, one deep solve per day). Any other value is refused.model— string — Label echoed in the result. Every value dispatches through the same registered engines; depth decides fast or multi-engine.antagonist— boolean — When true, forces one engine to act as adversarial red-team antagonist.
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_pre_mortemread-onlyExecutes an adversarial pre-mortem identifying failure modes and early warning indicators using empirical argument verification.
Parameters:
premise(required) — string — The strategic plan, architecture, or business premise to stress-test.horizonMonths— integer — Time horizon in months to simulate forward failure modes.
Hints: read-only yes · destructive no · idempotent yes · open-world no
ecca_decision_tournamentread-onlyEvaluates multi-option decision matrix using minimax regret and Pareto ranking over candidate pathways.
Parameters:
decisionContext(required) — string — Context of the decision to evaluate.options(required) — array — List of discrete options or strategic pathways.
Hints: read-only yes · destructive no · idempotent yes · open-world no
ecca_bts_divergenceread-onlyMeasures lexical and semantic divergence across candidate assertions to penalize sycophancy.
Parameters:
assertions(required) — array — Array of candidate assertions or claims to measure divergence for.
Hints: read-only yes · destructive no · idempotent yes · open-world no
ecca_refineread-onlyUse 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.
Parameters:
text(required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
ecca_researchread-onlyUse one keyed tier-quota slot and dispatch-ceiling reservation to fetch and grade studies from scholarly indexes; return fetched evidence and explicit gaps.
Parameters:
question(required) — stringniche— string
Hints: read-only yes · destructive no · idempotent yes · open-world yes
ecca_verifyIndependently answer a question and compare the candidate against deterministic panel agreement. Show named dissent; spends one solve.
Parameters:
question(required) — stringcandidate_answer(required) — string
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_psychologyPsychology research: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
Parameters:
question(required) — string
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_learningLearning and study skills: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
Parameters:
question(required) — string
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_nutritionNutrition and supplements: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
Parameters:
question(required) — string
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_moneyMoney and business: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
Parameters:
question(required) — string
Hints: read-only no · destructive no · idempotent no · open-world yes
ecca_claim_protocol_validateread-onlyCheck 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.
Parameters:
document(required) — object — The protocol document to check (docs/CLAIM_PROTOCOL.md).
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.