io.github.pipehero/pipehero
io.github.pipehero/pipehero · v0.1.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Debug webhooks from your AI agent: inspect and replay captured webhooks on localhost.
Source: https://github.com/pipehero/pipehero-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 25 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (delete_api_endpoint). Require confirmation before the agent calls them. |
What was checked
- https://mcp.pipehero.app/mcp: answers without auth
Public tools: list_tunnels, list_requests, get_request, replay_request, send_test_webhook, set_long_requests, set_ws_passthrough, list_api_collections, get_api_collection, get_api_endpoint, create_api_collection, upsert_api_endpoint, add_api_example, delete_api_endpoint, import_api_spec, export_api_collection, run_api_endpoint, save_captured_request, list_api_monitors, list_api_proposals, check_api_drift, get_api_share_link, share_api_endpoint, share_api_collection, list_api_runs
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-pipehero-pipehero-9018230e)