ECCA
Compare engine claims, inspect dissent and check study evidence for student questions.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"ecca": {
"url": "https://eccaai.com/api/mcp"
}
}
}遠端端點
https://eccaai.com/api/mcpstreamable-http它能做什麼
工具清單
工具（11）
⚪ecca_synthesize(query, model, depth, antagonist)
Cross-examines inquiry across configured frontier engines to synthesize the verified single best answer with measured lexical consensus scoring.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 64000,
"description": "The core inquiry, hypothesis, or decision challenge to synthesize."
},
"model": {
"type": "string",
"enum": [
"axiom-vector",
"axiom-core",
"axiom-reasoner",
"axiom-omni",
"axiom-sovereign"
],
"default": "axiom-reasoner",
"description": "Label echoed in the result. Every value dispatches through the same registered engines; depth decides fast or multi-engine."
},
"depth": {
"type": "string",
"enum": [
"intuitive",
"executive",
"pioneer",
"fast",
"deep"
],
"default": "executive",
"description": "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."
},
"antagonist": {
"type": "boolean",
"default": false,
"description": "When true, forces one engine to act as adversarial red-team antagonist."
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢ecca_pre_mortem(premise, horizonMonths)
Executes an adversarial pre-mortem identifying failure modes and early warning indicators using empirical argument verification.
輸入結構描述
{
"type": "object",
"properties": {
"premise": {
"type": "string",
"maxLength": 64000,
"description": "The strategic plan, architecture, or business premise to stress-test."
},
"horizonMonths": {
"type": "integer",
"default": 18,
"description": "Time horizon in months to simulate forward failure modes."
}
},
"required": [
"premise"
],
"additionalProperties": false
}🟢ecca_decision_tournament(decisionContext, options)
Evaluates multi-option decision matrix using minimax regret and Pareto ranking over candidate pathways.
輸入結構描述
{
"type": "object",
"properties": {
"decisionContext": {
"type": "string",
"maxLength": 32000,
"description": "Context of the decision to evaluate."
},
"options": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of discrete options or strategic pathways."
}
},
"required": [
"decisionContext",
"options"
],
"additionalProperties": false
}🟢ecca_bts_divergence(assertions)
Measures lexical and semantic divergence across candidate assertions to penalize sycophancy.
輸入結構描述
{
"type": "object",
"properties": {
"assertions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Array of candidate assertions or claims to measure divergence for."
}
},
"required": [
"assertions"
],
"additionalProperties": false
}🟢ecca_refine(text)
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.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"required": [
"text"
],
"additionalProperties": false
}🟢ecca_research(question, niche)
Use one keyed tier-quota slot and dispatch-ceiling reservation to fetch and grade studies from scholarly indexes; return fetched evidence and explicit gaps.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"niche": {
"type": "string",
"enum": [
"psychology",
"learning",
"nutrition",
"money"
]
}
},
"required": [
"question"
],
"additionalProperties": false
}🟢ecca_verify(question, candidate_answer)
Independently answer a question and compare the candidate against deterministic panel agreement. Show named dissent; spends one solve.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 8000
},
"candidate_answer": {
"type": "string",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"question",
"candidate_answer"
],
"additionalProperties": false
}🟢ecca_psychology(question)
Psychology research: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"required": [
"question"
],
"additionalProperties": false
}🟢ecca_learning(question)
Learning and study skills: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"required": [
"question"
],
"additionalProperties": false
}🟢ecca_nutrition(question)
Nutrition and supplements: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"required": [
"question"
],
"additionalProperties": false
}🟢ecca_money(question)
Money and business: refine the question, fetch studies, and show named claims before the verdict. Applies evidence and claims checks; spends one solve.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"type": "string",
"minLength": 1,
"maxLength": 2000
}
},
"required": [
"question"
],
"additionalProperties": false
}社群
證據