MCP MeasureMCP Measure

索引已观测

pipehero

Debug webhooks from your AI agent: inspect and replay captured webhooks on localhost.

我该使用它吗

质量与安全性

A
描述质量
99%
模式完整度
79%
命名质量
98%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~3,659token 数（工具定义）
~930 B典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 2.86%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "pipehero": {
      "url": "https://mcp.pipehero.app/mcp"
    }
  }
}

远程端点

https://mcp.pipehero.app/mcpstreamable-http

它能做什么

工具清单

工具（22）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_tunnels

List the user's Pipehero tunnels and whether each is currently online.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢list_requests(subdomain)

List recent webhooks/requests captured for a tunnel. Returns id, method, path, status and bodies.

输入模式

{
  "type": "object",
  "properties": {
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain"
  ]
}
🟢get_request(id, subdomain)

Get the full request and response (headers + body) of one captured webhook by id.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain",
    "id"
  ]
}
🔴replay_request(id, subdomain)

Replay a captured webhook to the user's localhost (the tunnel CLI must be running).

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain",
    "id"
  ]
}
🔴send_test_webhook(body, event, provider, subdomain)

Send a generated test webhook to the user's localhost (the tunnel CLI must be running). Provide a `provider` (stripe, github, shopify, clerk, slack, resend, paddle, polar, lemonsqueezy) and optional `event` for a realistic sample payload, or pass a custom JSON `body`. Pro plan required.

输入模式

{
  "type": "object",
  "properties": {
    "body": {
      "description": "Custom JSON body (overrides the template)",
      "type": "string"
    },
    "event": {
      "type": "string"
    },
    "provider": {
      "type": "string"
    },
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain",
    "provider"
  ]
}
🟡set_long_requests(enabled, subdomain)

Opt a tunnel into a 120-second ingress timeout instead of the 30-second default — for tool calls that legitimately run long, e.g. an MCP server exposed through the tunnel. Persists on the tunnel; pass enabled: false to revert to the 30-second default.

输入模式

{
  "type": "object",
  "properties": {
    "enabled": {
      "type": "boolean"
    },
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain",
    "enabled"
  ]
}
🟡set_ws_passthrough(enabled, subdomain)

Opt a tunnel into WebSocket passthrough, so an application-level WebSocket connection (e.g. a mobile/web app's own realtime feature) can be relayed to your localhost. Pro/Team plan required to enable; pass enabled: false to disable on any plan.

输入模式

{
  "type": "object",
  "properties": {
    "enabled": {
      "type": "boolean"
    },
    "subdomain": {
      "type": "string"
    }
  },
  "required": [
    "subdomain",
    "enabled"
  ]
}
🟢list_api_collections

List the workspace's API collections (saved endpoints with examples and environments). Start here to find a collection_id.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢get_api_collection(collection_id)

Get one collection's folders, endpoints (id, method, path, name, version, example count) and environments (with their variables).

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}
🟢get_api_endpoint(collection_id, endpoint_id, method, path)

Get one endpoint in full: description, parameters, headers, request body, saved response examples and its current `version`. Identify it by endpoint_id or by method + path.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "description": "Id from list_api_collections.",
      "type": "string"
    },
    "endpoint_id": {
      "description": "Id of the endpoint. Alternative to method + path.",
      "type": "string"
    },
    "method": {
      "description": "HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.",
      "type": "string"
    },
    "path": {
      "description": "Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.",
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}
🟡create_api_collection(description, name)

Create an empty API collection. Prefer import_api_spec when there is an OpenAPI file, and upsert_api_endpoint to fill it from the code.

输入模式

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string"
    },
    "name": {
      "type": "string"
    }
  },
  "required": [
    "name"
  ]
}
🟡upsert_api_endpoint(body, collection_id, description, folder, headers, ...)

Document an endpoint: creates it, or updates the existing one for the same method + path. Use it whenever you add or change a route in the code, so the docs stay true. Only the fields you send change. `path` may use :id, {id} or {{id}} for variables. `folder` is created by name if missing. Send `version` (from get_api_endpoint) to avoid overwriting a teammate's edit; a stale version is rejected.

输入模式

{
  "type": "object",
  "properties": {
    "body": {
      "description": "Example request body (any JSON). null clears it."
    },
    "collection_id": {
      "type": "string"
    },
    "description": {
      "type": "string"
    },
    "folder": {
      "description": "Folder name, e.g. Charges.",
      "type": "string"
    },
    "headers": {
      "items": {
        "properties": {
          "name": {
            "type": "string"
          },
          "value": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "value"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "kind": {
      "description": "`event` for a webhook your app sends.",
      "enum": [
        "http",
        "event"
      ],
      "type": "string"
    },
    "method": {
      "type": "string"
    },
    "name": {
      "description": "Short title, e.g. Create a charge. Defaults to METHOD /path.",
      "type": "string"
    },
    "params": {
      "description": "Documented fields.",
      "items": {
        "properties": {
          "description": {
            "type": "string"
          },
          "in": {
            "enum": [
              "path",
              "query",
              "header",
              "body"
            ],
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "required": {
            "type": "boolean"
          },
          "type": {
            "type": "string"
          }
        },
        "required": [
          "name"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "path": {
      "type": "string"
    },
    "version": {
      "type": "integer"
    }
  },
  "required": [
    "collection_id",
    "method",
    "path"
  ]
}
🟡add_api_example(body, collection_id, endpoint_id, headers, method, ...)

Save a response example on an endpoint (for instance the 402 your handler returns for a declined card). Replaces the example with the same name, so it is safe to repeat.

输入模式

{
  "type": "object",
  "properties": {
    "body": {
      "description": "Example response body (any JSON)."
    },
    "collection_id": {
      "description": "Id from list_api_collections.",
      "type": "string"
    },
    "endpoint_id": {
      "description": "Id of the endpoint. Alternative to method + path.",
      "type": "string"
    },
    "headers": {
      "items": {
        "properties": {
          "name": {
            "type": "string"
          },
          "value": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "value"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "method": {
      "description": "HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.",
      "type": "string"
    },
    "name": {
      "description": "e.g. Card declined.",
      "type": "string"
    },
    "path": {
      "description": "Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.",
      "type": "string"
    },
    "status": {
      "type": "integer"
    },
    "status_text": {
      "type": "string"
    }
  },
  "required": [
    "collection_id",
    "name",
    "status"
  ]
}
🔴delete_api_endpoint(collection_id, endpoint_id, method, path)

Delete an endpoint and its examples. Use when the route no longer exists in the code. Cannot be undone.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "description": "Id from list_api_collections.",
      "type": "string"
    },
    "endpoint_id": {
      "description": "Id of the endpoint. Alternative to method + path.",
      "type": "string"
    },
    "method": {
      "description": "HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.",
      "type": "string"
    },
    "path": {
      "description": "Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.",
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}
⚪import_api_spec(collection_id, content, format, name)

Import an OpenAPI 3.x document (as JSON), a Postman v2.x collection (JSON) or a curl command into a new collection, or into `collection_id`. All or nothing, and plan limits are checked first. Credentials are never imported (they become variables). Convert YAML to JSON before sending.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "description": "Add to this collection instead of creating one.",
      "type": "string"
    },
    "content": {
      "description": "The document (object or JSON string), or the curl command."
    },
    "format": {
      "enum": [
        "openapi",
        "postman",
        "har",
        "curl"
      ],
      "type": "string"
    },
    "name": {
      "description": "Name for the new collection.",
      "type": "string"
    }
  },
  "required": [
    "format",
    "content"
  ]
}
🟢export_api_collection(collection_id, format)

Export a collection as an OpenAPI 3.1 or Postman 2.1 document. Handy to read the whole API at once.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "type": "string"
    },
    "format": {
      "enum": [
        "openapi",
        "postman"
      ],
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}
🔴run_api_endpoint(collection_id, confirm_write_to_prod, endpoint_id, environment, method, ...)

Send an endpoint against an environment and return the real response (status, headers, body up to 20 KB). A `local` environment goes through the user's tunnel to their localhost (the CLI must be running); staging/prod are sent from Pipehero's cloud (Pro/Team) to public addresses only. Sending to a `prod` environment with a write method needs confirm_write_to_prod: true, which you should only pass after the user agrees. Use it to check that the code you wrote behaves as documented.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "description": "Id from list_api_collections.",
      "type": "string"
    },
    "confirm_write_to_prod": {
      "type": "boolean"
    },
    "endpoint_id": {
      "description": "Id of the endpoint. Alternative to method + path.",
      "type": "string"
    },
    "environment": {
      "description": "Environment name or id, e.g. local.",
      "type": "string"
    },
    "method": {
      "description": "HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.",
      "type": "string"
    },
    "path": {
      "description": "Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.",
      "type": "string"
    },
    "variables": {
      "additionalProperties": {
        "type": "string"
      },
      "description": "Values for {{variables}} the environment doesn't define, e.g. {\"id\": \"ch_123\"}.",
      "type": "object"
    }
  },
  "required": [
    "collection_id",
    "environment"
  ]
}
🟡save_captured_request(collection_id, endpoint_id, folder, method, path, ...)

Document a real request captured by a tunnel (get its id from list_requests). If an endpoint already covers the route, the response is added to it as an example; otherwise an endpoint is created from the request. Credentials, cookies and signatures are replaced by {{variables}} and only JSON bodies are kept. A response already saved as an example is not duplicated. Use it to document webhooks and calls you have only seen in traffic.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "type": "string"
    },
    "endpoint_id": {
      "description": "Add the example to this endpoint instead of matching by route. Alternative to method + path.",
      "type": "string"
    },
    "folder": {
      "description": "Folder for a newly created endpoint, created by name if missing.",
      "type": "string"
    },
    "method": {
      "description": "With path: the endpoint that should receive the example.",
      "type": "string"
    },
    "path": {
      "type": "string"
    },
    "request_id": {
      "description": "Id of the captured request, from list_requests.",
      "type": "string"
    },
    "tunnel": {
      "description": "Subdomain of the tunnel that captured the request.",
      "type": "string"
    }
  },
  "required": [
    "collection_id",
    "tunnel",
    "request_id"
  ]
}
🟢list_api_monitors(collection_id)

See which endpoints of a collection are checked on a schedule (Pro/Team monitors) and how they are doing: state (healthy, failing, blip, paused, waiting), the last check with its status, latency and error, and since when it has been failing. Use it to find out what is broken in staging or production, then read the endpoint and its code. Read-only: people decide what to monitor.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}
🟢list_api_proposals

See what happened to the changes you proposed. Some workspaces review AI changes: your write tools then answer `pending_review` and change nothing until a teammate approves. This lists the latest proposals with their status (pending, approved, rejected with the reviewer's reason, or failed with why) so you can tell whether a change went through.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢check_api_drift(collection_id, limit, tunnel)

Compare a collection's docs with the real traffic a tunnel captured (Pro/Team). Returns routes nobody documented, status codes with no example, response or request fields missing from every example (or with another type), undocumented query parameters, and documented fields that never appear. Each finding includes `request_id` of the newest request that shows it: pass it to save_captured_request to add it to the docs, or fix the docs with upsert_api_endpoint and add_api_example. Use it to find out what drifted after a code change.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "type": "string"
    },
    "limit": {
      "description": "How many recent requests to compare (default 200, max 500).",
      "type": "integer"
    },
    "tunnel": {
      "description": "Subdomain of the tunnel whose traffic to compare.",
      "type": "string"
    }
  },
  "required": [
    "collection_id",
    "tunnel"
  ]
}
🟢list_api_runs(collection_id, endpoint_id, limit, method, path)

Recent runs of an endpoint (newest first, default 5): who/what was sent and what came back. Use to see what happened the last time it was run.

输入模式

{
  "type": "object",
  "properties": {
    "collection_id": {
      "description": "Id from list_api_collections.",
      "type": "string"
    },
    "endpoint_id": {
      "description": "Id of the endpoint. Alternative to method + path.",
      "type": "string"
    },
    "limit": {
      "description": "1 to 20.",
      "type": "integer"
    },
    "method": {
      "description": "HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.",
      "type": "string"
    },
    "path": {
      "description": "Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.",
      "type": "string"
    }
  },
  "required": [
    "collection_id"
  ]
}

推荐提示词

explore_workflow
List available [items], then get details for each one using pipehero
预期工具： list_tunnelsget_request
fetch_info
Fetch [information type] using pipehero
预期工具： get_request
list_items
List all [items] available in pipehero
预期工具： list_tunnels
retrieve_data
Get details about [item] from pipehero
预期工具： get_request
browse_collection
Show me the [collection] from pipehero
预期工具： list_tunnels

社区

评价此服务器

证据

最近观测

已验证未记录版本22 个工具
已验证未记录版本7 个工具