此 MCP 可以做什么
Captures, inspects, replays, tests, monitors, and documents webhooks and API endpoints through local tunnels.
功能
工具
22
工具
add_api_example
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.
幂等
输入模式
{'type': 'object', 'required': ['collection_id', 'name', 'status'], 'properties': {'body': {'description': 'Example response body (any JSON).'}, 'name': {'type': 'string', 'description': 'e.g. Card declined.'}, 'path': {'type': 'string', 'description': 'Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.'}, 'method': {'type': 'string', 'description': 'HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.'}, 'status': {'type': 'integer'}, 'headers': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'value'], 'properties': {'name': {'type': 'string'}, 'value': {'type': 'string'}}}}, 'endpoint_id': {'type': 'string', 'description': 'Id of the endpoint. Alternative to method + path.'}, 'status_text': {'type': 'string'}, 'collection_id': {'type': 'string', 'description': 'Id from list_api_collections.'}}}
check_api_drift
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.
只读
输入模式
{'type': 'object', 'required': ['collection_id', 'tunnel'], 'properties': {'limit': {'type': 'integer', 'description': 'How many recent requests to compare (default 200, max 500).'}, 'tunnel': {'type': 'string', 'description': 'Subdomain of the tunnel whose traffic to compare.'}, 'collection_id': {'type': 'string'}}}
create_api_collection
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', 'required': ['name'], 'properties': {'name': {'type': 'string'}, 'description': {'type': 'string'}}}
delete_api_endpoint
Delete an endpoint and its examples. Use when the route no longer exists in the code. Cannot be undone.
可能执行破坏性操作
幂等
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'path': {'type': 'string', 'description': 'Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.'}, 'method': {'type': 'string', 'description': 'HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.'}, 'endpoint_id': {'type': 'string', 'description': 'Id of the endpoint. Alternative to method + path.'}, 'collection_id': {'type': 'string', 'description': 'Id from list_api_collections.'}}}
export_api_collection
Export a collection as an OpenAPI 3.1 or Postman 2.1 document. Handy to read the whole API at once.
只读
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'format': {'enum': ['openapi', 'postman'], 'type': 'string'}, 'collection_id': {'type': 'string'}}}
get_api_collection
Get one collection's folders, endpoints (id, method, path, name, version, example count) and environments (with their variables).
只读
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'collection_id': {'type': 'string'}}}
get_api_endpoint
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.
只读
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'path': {'type': 'string', 'description': 'Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.'}, 'method': {'type': 'string', 'description': 'HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.'}, 'endpoint_id': {'type': 'string', 'description': 'Id of the endpoint. Alternative to method + path.'}, 'collection_id': {'type': 'string', 'description': 'Id from list_api_collections.'}}}
get_request
Get the full request and response (headers + body) of one captured webhook by id.
只读
输入模式
{'type': 'object', 'required': ['subdomain', 'id'], 'properties': {'id': {'type': 'string'}, 'subdomain': {'type': 'string'}}}
import_api_spec
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', 'required': ['format', 'content'], 'properties': {'name': {'type': 'string', 'description': 'Name for the new collection.'}, 'format': {'enum': ['openapi', 'postman', 'har', 'curl'], 'type': 'string'}, 'content': {'description': 'The document (object or JSON string), or the curl command.'}, 'collection_id': {'type': 'string', 'description': 'Add to this collection instead of creating one.'}}}
list_api_collections
List the workspace's API collections (saved endpoints with examples and environments). Start here to find a collection_id.
只读
输入模式
{'type': 'object', 'properties': {}}
list_api_monitors
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.
只读
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'collection_id': {'type': 'string'}}}
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.
只读
输入模式
{'type': 'object', 'properties': {}}
list_api_runs
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.
只读
输入模式
{'type': 'object', 'required': ['collection_id'], 'properties': {'path': {'type': 'string', 'description': 'Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.'}, 'limit': {'type': 'integer', 'description': '1 to 20.'}, 'method': {'type': 'string', 'description': 'HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.'}, 'endpoint_id': {'type': 'string', 'description': 'Id of the endpoint. Alternative to method + path.'}, 'collection_id': {'type': 'string', 'description': 'Id from list_api_collections.'}}}
list_requests
List recent webhooks/requests captured for a tunnel. Returns id, method, path, status and bodies.
只读
输入模式
{'type': 'object', 'required': ['subdomain'], 'properties': {'subdomain': {'type': 'string'}}}
list_tunnels
List the user's Pipehero tunnels and whether each is currently online.
只读
输入模式
{'type': 'object', 'properties': {}}
replay_request
Replay a captured webhook to the user's localhost (the tunnel CLI must be running).
可能执行破坏性操作
可访问外部资源
输入模式
{'type': 'object', 'required': ['subdomain', 'id'], 'properties': {'id': {'type': 'string'}, 'subdomain': {'type': 'string'}}}
run_api_endpoint
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.
可能执行破坏性操作
可访问外部资源
输入模式
{'type': 'object', 'required': ['collection_id', 'environment'], 'properties': {'path': {'type': 'string', 'description': 'Route path as written in the code, e.g. /v1/charges/:id or /v1/charges/{id}.'}, 'method': {'type': 'string', 'description': 'HTTP method of the route, e.g. POST. Use with path instead of endpoint_id.'}, 'variables': {'type': 'object', 'description': 'Values for {{variables}} the environment doesn\'t define, e.g. {"id": "ch_123"}.', 'additionalProperties': {'type': 'string'}}, 'endpoint_id': {'type': 'string', 'description': 'Id of the endpoint. Alternative to method + path.'}, 'environment': {'type': 'string', 'description': 'Environment name or id, e.g. local.'}, 'collection_id': {'type': 'string', 'description': 'Id from list_api_collections.'}, 'confirm_write_to_prod': {'type': 'boolean'}}}
save_captured_request
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.
幂等
输入模式
{'type': 'object', 'required': ['collection_id', 'tunnel', 'request_id'], 'properties': {'path': {'type': 'string'}, 'folder': {'type': 'string', 'description': 'Folder for a newly created endpoint, created by name if missing.'}, 'method': {'type': 'string', 'description': 'With path: the endpoint that should receive the example.'}, 'tunnel': {'type': 'string', 'description': 'Subdomain of the tunnel that captured the request.'}, 'request_id': {'type': 'string', 'description': 'Id of the captured request, from list_requests.'}, 'endpoint_id': {'type': 'string', 'description': 'Add the example to this endpoint instead of matching by route. Alternative to method + path.'}, 'collection_id': {'type': 'string'}}}
send_test_webhook
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.
可能执行破坏性操作
可访问外部资源
输入模式
{'type': 'object', 'required': ['subdomain', 'provider'], 'properties': {'body': {'type': 'string', 'description': 'Custom JSON body (overrides the template)'}, 'event': {'type': 'string'}, 'provider': {'type': 'string'}, 'subdomain': {'type': 'string'}}}
set_long_requests
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.
幂等
输入模式
{'type': 'object', 'required': ['subdomain', 'enabled'], 'properties': {'enabled': {'type': 'boolean'}, 'subdomain': {'type': 'string'}}}
set_ws_passthrough
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.
幂等
输入模式
{'type': 'object', 'required': ['subdomain', 'enabled'], 'properties': {'enabled': {'type': 'boolean'}, 'subdomain': {'type': 'string'}}}
upsert_api_endpoint
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.
幂等
输入模式
{'type': 'object', 'required': ['collection_id', 'method', 'path'], 'properties': {'body': {'description': 'Example request body (any JSON). null clears it.'}, 'kind': {'enum': ['http', 'event'], 'type': 'string', 'description': '`event` for a webhook your app sends.'}, 'name': {'type': 'string', 'description': 'Short title, e.g. Create a charge. Defaults to METHOD /path.'}, 'path': {'type': 'string'}, 'folder': {'type': 'string', 'description': 'Folder name, e.g. Charges.'}, 'method': {'type': 'string'}, 'params': {'type': 'array', 'items': {'type': 'object', 'required': ['name'], 'properties': {'in': {'enum': ['path', 'query', 'header', 'body'], 'type': 'string'}, 'name': {'type': 'string'}, 'type': {'type': 'string'}, 'required': {'type': 'boolean'}, 'description': {'type': 'string'}}}, 'description': 'Documented fields.'}, 'headers': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'value'], 'properties': {'name': {'type': 'string'}, 'value': {'type': 'string'}}}}, 'version': {'type': 'integer'}, 'description': {'type': 'string'}, 'collection_id': {'type': 'string'}}}
历史
近期工具变更
已添加
list_api_runs
2026年9月23日 02:47
已添加
check_api_drift
2026年9月23日 02:47
已添加
list_api_proposals
2026年9月23日 02:47
已添加
list_api_monitors
2026年9月23日 02:47
已添加
save_captured_request
2026年9月23日 02:47
已添加
run_api_endpoint
2026年9月23日 02:47
已添加
export_api_collection
2026年9月23日 02:47
已添加
import_api_spec
2026年9月23日 02:47
已添加
delete_api_endpoint
2026年9月23日 02:47
已添加
add_api_example
2026年9月23日 02:47
已添加
upsert_api_endpoint
2026年9月23日 02:47
已添加
create_api_collection
2026年9月23日 02:47
已添加
get_api_endpoint
2026年9月23日 02:47
已添加
get_api_collection
2026年9月23日 02:47
已添加
list_api_collections
2026年9月23日 02:47
已添加
set_ws_passthrough
2026年9月17日 12:45
已添加
set_long_requests
2026年9月17日 12:45
已添加
send_test_webhook
2026年9月17日 12:45
已添加
replay_request
2026年9月17日 12:45
已添加
get_request
2026年9月17日 12:45
已添加
list_requests
2026年9月17日 12:45
已添加
list_tunnels
2026年9月17日 12:45
发现
类似的 MCP 服务器
TinyFn
io.tinyfn/tinyfn
Offers deterministic utility functions for mathematics, conversions, validation, hashing, encoding, arrays, dates, colors, and pa…
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
Vee3
io.github.Vee3io/vee3
Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…
Courier
io.github.trycourier/courier
Provides notification delivery infrastructure for users, tenants, lists, templates, preferences, journeys, automations, brands, a…
GripForge
io.github.gripforgeai/mcp
Generates, rigs, animates, analyzes, and packages game characters, weapons, armor, effects, environments, and engine-ready assets.
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
apis-io
io.apis/apis-io
Provides catalog search, comparison, scoring, enrichment, lists, and dataset exports for APIs, providers, specifications, workflo…