agiscorecard-web3-route
Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.
我該用這個嗎
品質與安全性
發現項目(1)
- LOW在 fetch 中
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": {
"agiscorecard-web3-route": {
"url": "https://route.agiscorecard.com/mcp"
}
}
}遠端端點
https://route.agiscorecard.com/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢search(query)
Search this server’s public AI/Web3 tools and citation pages. English and Chinese names supported. Empty query lists the available worksheets.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 160
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title",
"url"
],
"additionalProperties": false
}
}
},
"required": [
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢fetch(id)
Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"enum": [
"route"
]
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object",
"properties": {
"version": {
"type": "string"
},
"revision": {
"type": "string"
},
"reviewedAt": {
"type": "string"
},
"evidenceType": {
"type": "string"
}
},
"required": [
"version",
"revision",
"reviewedAt",
"evidenceType"
],
"additionalProperties": false
}
},
"required": [
"id",
"title",
"text",
"url",
"metadata"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢plan_fallback_routes(currency, budget, maxLatencyMs, minSuccess, maxAttempts, ...)
Route Lab compares short supplier sequences using entered cost, success and latency assumptions. It checks the worst-case total against your budget before sorting feasible options by expected cost. It is an offline planning tool; no model or payment is called. Offline planning only. No live requests, model judge, payment, dynamic bandit or production routing. Retrieve route with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
輸入結構描述
{
"type": "object",
"properties": {
"currency": {
"type": "string",
"maxLength": 131072,
"description": "Currency (preserve source text; decimal amounts must stay strings)"
},
"budget": {
"type": "string",
"maxLength": 131072,
"description": "Total budget (preserve source text; decimal amounts must stay strings)"
},
"maxLatencyMs": {
"type": "number",
"description": "Total latency bound (ms)"
},
"minSuccess": {
"type": "number",
"description": "Minimum success probability (0–1)"
},
"maxAttempts": {
"type": "number",
"description": "Maximum attempts"
},
"candidates": {
"maxItems": 200,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"maxLength": 131072,
"description": "Record ID (preserve source text; decimal amounts must stay strings)"
},
"cost": {
"type": "string",
"maxLength": 131072,
"description": "Cost (preserve source text; decimal amounts must stay strings)"
},
"success": {
"type": "number",
"description": "Success probability (0–1)"
},
"latencyMs": {
"type": "number",
"description": "Attempt latency bound (ms)"
},
"allowed": {
"type": "boolean",
"description": "Allowed by your policy"
}
},
"required": [
"id",
"cost",
"success",
"latencyMs",
"allowed"
],
"additionalProperties": false,
"description": "Exact record structure; the engine additionally checks bounds, dates, identifiers and cross-field constraints."
},
"description": "Candidates"
}
},
"required": [
"currency",
"budget",
"maxLatencyMs",
"minSuccess",
"maxAttempts",
"candidates"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false,
"description": "Exact record structure; the engine additionally checks bounds, dates, identifiers and cross-field constraints."
}輸出結構描述
{
"type": "object",
"properties": {
"toolId": {
"type": "string"
},
"version": {
"type": "string"
},
"revision": {
"type": "string"
},
"processing": {
"type": "string"
},
"evidenceStatus": {
"type": "string"
},
"citation": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"methodUrl": {
"type": "string"
},
"reviewedAt": {
"type": "string"
},
"scope": {
"type": "string"
}
},
"required": [
"title",
"url",
"methodUrl",
"reviewedAt",
"scope"
],
"additionalProperties": false
},
"officialReferences": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"relationship": {
"type": "string"
}
},
"required": [
"title",
"url",
"relationship"
],
"additionalProperties": false
}
},
"limitations": {
"type": "string"
},
"report": {
"type": "object",
"properties": {
"version": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"metrics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"label": {
"type": "string"
},
"value": {
"type": [
"string",
"number"
]
}
},
"required": [
"label",
"value"
],
"additionalProperties": false
}
},
"tables": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"columns": {
"type": "array",
"items": {
"type": "string"
}
},
"rows": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": [
"string",
"number",
"boolean",
"null"
]
}
}
}
},
"required": [
"title",
"columns",
"rows"
],
"additionalProperties": false
}
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"data": {}
},
"required": [
"version",
"title",
"summary",
"metrics",
"tables",
"notes",
"data"
],
"additionalProperties": false
}
},
"required": [
"toolId",
"version",
"revision",
"processing",
"evidenceStatus",
"citation",
"officialReferences",
"limitations",
"report"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}社群
證據