Cartograph is an MCP server that provides task-shaped repository context for coding agents by analyzing and mapping dependencies in code repositories.
From the registry: Local-first reusable implementation registry for AI agents and versioned widgets.
$ npm install -g @anthony-maio/cartographPlease install the `cartograph` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install cartograph** — Install the cartograph CLI globally Run: `npm install -g @anthony-maio/cartograph` (https://www.npmjs.com/package/@anthony-maio/cartograph)
Canonical MCP server config (stdio transport):
- command: `cartograph`
- args: ["mcp"]
- optional environment variables:
- `CARTOGRAPH_API_KEY`: API key for LLM providers (gemini/openai/openrouter). Not needed for ollama or static analysis (example: `<your-api-key>`)
Note: Task-shaped repo context for coding agents. Tools: analyze_repo, get_file_contents, build_task_packet. Also ships Claude Code plugin and OpenClaw skill pack.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CARTOGRAPH_API_KEYrequiredAPI key for accessing certain features.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.