codegraph vs n8n-mcp
Two of the top projects in MCP servers for developers, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
codegraph
Local code knowledge graph served to coding agents over MCP
n8n-mcp
MCP server exposing n8n node docs, templates and workflow management to AI assistants
Verdict
codegraph ranks higher, 82 to 76. Of the 5 score parts we measure for both, codegraph leads on 2, n8n-mcp on 1 and 2 are even.
- Adoptioncodegraph leads by 26 points, 96 to 70: a wide gap.
- FreshnessEven at 100.
- Maintenancen8n-mcp leads by 4 points, 93 to 89: close to even.
- Easy to runEven at 50.
- Agent-readycodegraph leads by 15 points, 85 to 70: a wide gap.
Pick codegraph if you are
Developers using AI coding agents on mid-to-large codebases
- Runs locally; no Node.js needed, ships as a bundled installer or npm package
- One `codegraph install` configures MCP for nine named agents and IDEs
Pick n8n-mcp if you are
Developers building n8n workflows with Claude, Cursor or other MCP clients
- Node, template and validation tools (search_nodes, get_node, validate_workflow) cover core and community nodes
- 21 management tools create, patch, autofix and test workflows on a connected n8n instance
| What we compare | codegraph | n8n-mcp |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 96, widely used | 70, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 89, healthy | 93, healthy |
| Easy to run | 50, easy | 50, easy |
| Agent-ready | 85, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 74.2k | 23.1k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | C | TypeScript |
| Docker | No | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Mentioned | Not stated |
codegraph
CodeGraph indexes a project into a local graph of symbols, call edges and dependencies under `.codegraph/`, then exposes it to coding agents through an MCP server. Agents can fetch relevant source, call paths and change impact in one call instead of grepping and reading files. `codegraph install` wires it into Claude Code, Cursor, Codex CLI, opencode, Gemini CLI, Kiro, GitHub Copilot and others, and auto-sync keeps the index current.
Who it is for: Developers using AI coding agents on mid-to-large codebases
Strengths
- Runs locally; no Node.js needed, ships as a bundled installer or npm package
- One `codegraph install` configures MCP for nine named agents and IDEs
- Covers 30+ languages, including TypeScript, Python, Go, Rust, Java, C#, Swift
- Watches files and updates the graph automatically; no manual re-index
Weaknesses
- README admits about 80% more retrieval context stays resident in long sessions
- Published benchmarks are the author's, on 7 repos with one question each
- No Docker or compose setup; install is via curl/PowerShell script or npm
- Hosted CodeGraph platform is a waitlist product, separate from this repo
- no GPU
n8n-mcp
n8n-MCP is a TypeScript MCP server that gives AI assistants searchable access to 3,135 n8n nodes (840 core, 2,295 community), their property schemas, and 2,352 workflow templates. With an n8n API URL and key configured, it also creates, updates, validates, tests and deploys workflows on a live n8n instance. It can be used through a hosted dashboard or self-hosted via npx, Docker or Railway.
Who it is for: Developers building n8n workflows with Claude, Cursor or other MCP clients
Strengths
- Node, template and validation tools (search_nodes, get_node, validate_workflow) cover core and community nodes
- 21 management tools create, patch, autofix and test workflows on a connected n8n instance
- Hosted option with free tier of 100 tool calls/day, or self-host via npx, Docker or Railway
- Setup guides for Claude Code, Cursor, VS Code, Windsurf and Codex
Weaknesses
- Operation coverage is 66.5% and docs coverage 86%, so some nodes lack detail
- Management tools need N8N_API_URL and N8N_API_KEY; some also need a separate MCP access token
- README warns AI edits to production workflows are unpredictable; backups needed
- Split-host n8n instance-level MCP (N8N_MCP_BASE_URL) is not supported
- no GPU
- Docker + Compose
- Needs n8n instance (optional, for management tools), n8n API key
More in MCP servers for developers
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.