Local, safety-first MCP server for Rapid7 InsightConnect / Automation
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"rapid7-insightconnect-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Rapid7 InsightConnect MCP [](https://github.com/sonadztux/rapid7-insightconnect-mcp/actions/workflows/ci.yml) Use Rapid7 InsightConnect from an MCP-compatible AI assistant to find workflows, inspect jobs and artifacts, export snippets, and optionally run or cancel workflows. > **Unofficial community project.** This project is independently developed and is not an official Rapid7 product. It is not provided, maintained, endorsed, or supported by Rapid7. References to Rapid7 and InsightConnect are used only to describe compatibility with Rapid7 InsightConnect. - **Harness-agnostic:** your AI client owns MCP registration; this project only provides the MCP server. - **Local by design:** there is no hosted middle service. - **Read-only by default:** execution and cancellation stay disabled until you explicitly enable them. - **API keys stay out of chat:** setup collects the key through a one-time local browser page. ## Quick start You need an MCP-capable client, [`uv`](https://docs.astral.sh/uv/) with Python 3.11+, and a Rapid7 API key. The MCP executable is always: ```sh uvx rapid7-insightconnect-mcp ``` ### 1. Add it to your AI client **Claude Code** ```sh claude mcp add --transport stdio --scope user rapid7-insightconnect -- \ uvx rapid7-insightconnect-mcp ``` **Codex** ```sh codex mcp add rapid7-insightconnect -- \ uvx rapid7-insightconnect-mcp ``` For other local MCP clients, register a stdio server with: ```text Command: uvx Arguments: rapid7-insightconnect-mcp ``` The implementation does not detect or modify your AI client's configuration. ### 2. Connect Rapid7 Open a new AI session and ask: > **Connect my Rapid7 InsightConnect account.** The MCP should call its `setup` tool and open a one-time local page. Choose your Rapid7 region, paste the API key, and leave writes disabled for your first session. The API key goes directly to the local MC…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.