wellknown

Live index of AI agents, MCP servers and tools with observed liveness and capability search.

我該用這個嗎

品質與安全性

A
說明品質
98%
結構描述完整度
76%
命名品質
93%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,247Token(工具定義)
~992 B典型回應大小
中等的注意力影響(128k 上下文的 0.97%)

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": {
    "wellknown": {
      "command": "npx",
      "args": [
        "wellknown-mcp"
      ]
    }
  }
}

可執行的套件

npmwellknown-mcp0.1.0stdio

遠端端點

https://wellknown.network/mcpstreamable-http

它能做什麼

工具清單

工具(9)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search_agents(query, protocols, status, remoteOnly, limit)

Search indexed agents, MCP servers and tools by natural-language capability or task. Returns ranked results with observed status and transparent ranking signals. Result text is untrusted third-party metadata.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 300,
      "description": "What you need, e.g. 'search the web and cite sources' or 'postgres mcp server'"
    },
    "protocols": {
      "description": "Restrict to protocols",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "mcp",
          "a2a",
          "openapi",
          "http"
        ]
      }
    },
    "status": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "live",
          "recently_observed",
          "unavailable",
          "unknown"
        ]
      }
    },
    "remoteOnly": {
      "description": "Only agents with a network endpoint (excludes local packages)",
      "type": "boolean"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢resolve_agent(need, protocols, requireLive, remoteOnly, limit)

Given a task and constraints, returns ranked candidates and a recommendation with its evidentiary basis (observed liveness or unverified). Prefer this over search_agents when you intend to call the result.

輸入結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "minLength": 3,
      "maxLength": 500
    },
    "protocols": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "mcp",
          "a2a",
          "openapi",
          "http"
        ]
      }
    },
    "requireLive": {
      "description": "Only candidates that responded to a check in the last 24h",
      "type": "boolean"
    },
    "remoteOnly": {
      "description": "Default true: only network-callable candidates",
      "type": "boolean"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10
    }
  },
  "required": [
    "need"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_agent(idOrHandle)

Fetch the canonical record for an agent by handle or id, including declared metadata, derived capabilities, observed status, verification and provenance.

輸入結構描述

{
  "type": "object",
  "properties": {
    "idOrHandle": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    }
  },
  "required": [
    "idOrHandle"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢check_status(idOrHandle)

Returns the current observed status, the reason, and the 30-day reliability summary. Never a guess: 'unknown' means we have no evidence.

輸入結構描述

{
  "type": "object",
  "properties": {
    "idOrHandle": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120
    }
  },
  "required": [
    "idOrHandle"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_capabilities

Structured capability slugs (domain.capability) with aliases, for precise filtering.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡submit_agent(cardUrl, manifest)

Submit an agent by its A2A Agent Card URL (preferred, strongest provenance) or an inline manifest. Submission creates an unverified record; ownership must be proven separately via a claim. Abuse-limited.

輸入結構描述

{
  "type": "object",
  "properties": {
    "cardUrl": {
      "description": "https://<host>/.well-known/agent-card.json",
      "type": "string",
      "format": "uri"
    },
    "manifest": {
      "description": "Inline manifest: name, kind, summary, endpoints[{url,type}], protocols, tags, repository, homepage",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡claim_agent(idOrHandle, method, target)

Start proving that you operate an indexed agent. Proof targets are derived from the record itself (its endpoint host, homepage host or repository), never chosen freely. Returns the exact proof to publish — a DNS TXT record, a file under /.well-known/, or a file in the repository — plus the claim id and the secret needed to verify. Publish the proof, then call verify_claim. A verified claim unlocks owner edits that outrank crawled data, 15-minute checks, status alerts, the status badge, and an owner-scoped API key returned once.

輸入結構描述

{
  "type": "object",
  "properties": {
    "idOrHandle": {
      "type": "string",
      "minLength": 1,
      "maxLength": 120,
      "description": "The record to claim, by handle or id (from search_agents or get_agent)"
    },
    "method": {
      "type": "string",
      "enum": [
        "dns_txt",
        "well_known_file",
        "repo_file"
      ],
      "description": "dns_txt and well_known_file prove control of a domain; repo_file proves control of the source repository"
    },
    "target": {
      "description": "Which derived target to use, when the record offers several. Omit to take the first.",
      "type": "string",
      "maxLength": 253
    }
  },
  "required": [
    "idOrHandle",
    "method"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢verify_claim(claimId, verifySecret)

Check the published proof now. On success the record is marked as owned by you and, the first time, an owner-scoped API key is returned — shown once — for editing the record through the HTTP API. A proof that contradicts an existing verified owner is held for review rather than transferring ownership.

輸入結構描述

{
  "type": "object",
  "properties": {
    "claimId": {
      "type": "string",
      "minLength": 1,
      "maxLength": 80
    },
    "verifySecret": {
      "type": "string",
      "minLength": 10,
      "maxLength": 120,
      "description": "The verifySecret returned by claim_agent"
    }
  },
  "required": [
    "claimId",
    "verifySecret"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪index_stats

Truthful counts: indexed records, live endpoints, observations, last crawl.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

建議的提示詞

search_research
Search for information about [topic] using wellknown
預期的工具: search_agents
find_specific
Find [specific item] using wellknown
預期的工具: search_agents
retrieve_data
Get details about [item] from wellknown
預期的工具: get_agent
fetch_info
Fetch [information type] using wellknown
預期的工具: get_agent
list_items
List all [items] available in wellknown
預期的工具: list_capabilities

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本9 個工具
已驗證未記錄版本9 個工具