Analyzes codebases to create structured maps of routes, features, and flows for AI agents to use as context.
Also known as itsflaid/devmap, @flaid/devmap
- Stars
- 11
- Tools
- —
- Downloads, 30 days
- 2,579
- Latest version
- 0.9.0
- Last commit
- Nov 14, 2026
- License
- MIT
What is devmap MCP?
devmap analyzes codebases to create structured maps of routes, features, and flows for AI agents to use as context.
Summary generated from the project's README
About devmap MCP server
Providing AI agents with a structured understanding of your codebase is what devmap enables. It functions as a CLI tool that performs static analysis and optional AI interpretation to build reusable maps of routes, features, and critical files. This allows developers to avoid re-explaining their project structure to every new AI chat session by using generated files like .devmap/index.json and DEVMAP.md as a persistent context layer.
Users can run the server locally via npx or install it globally using npm. To enable AI-driven interpretation, you must provide an API key for Groq, OpenRouter, or a custom OpenAI-compatible endpoint during the initialization process. The tool is designed with privacy in mind, ensuring that full repository source remains local and is not sent wholesale to AI models. When running as an MCP server via the devmap mcp command, it provides specific tools such as devmap_overview, devmap_map, and devmap_flow to help agents navigate your project through structured JSON responses.
What you can do with it
- 1Map project architecture for agentsAn AI agent can use the server to understand the entry points and critical files of a repository without reading every file.
- 2Analyze specific code featuresA developer can request a scoped map of a single feature or file to provide precise context to a model.
- 3Trace application logic flowsYou can ask the AI to identify and explain the top curated flows within your application.
Written from the project's README. Every use case is checked against a quote from it.
How to install devmap MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall devmap MCP in Claude Code
$ claude mcp add devmap -- npx -y @flaid/devmapInstall devmap MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"devmap": {
"command": "npx",
"args": [
"-y",
"@flaid/devmap"
]
}
}
}Install devmap MCP in VS Code
.vscode/mcp.json
{
"servers": {
"devmap": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@flaid/devmap"
]
}
}
}Install devmap MCP in VS Code CLI
$ code --add-mcp '{"name":"devmap","type":"stdio","command":"npx","args":["-y","@flaid/devmap"]}'Install devmap MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"devmap": {
"command": "npx",
"args": [
"-y",
"@flaid/devmap"
]
}
}
}Install devmap MCP in Codex
$ codex mcp add devmap -- npx -y @flaid/devmapInstall devmap MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.devmap] command = "npx" args = ["-y", "@flaid/devmap"]
Install devmap MCP in Gemini CLI
$ gemini mcp add -s user devmap npx -- -y @flaid/devmapInstall devmap MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"devmap": {
"command": "npx",
"args": [
"-y",
"@flaid/devmap"
]
}
}
}Configuration
GROQ_API_KEYOPENROUTER_API_KEY
| Name | Description | |
|---|---|---|
| GROQ_API_KEY | — | |
| OPENROUTER_API_KEY | — |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubDevMap
Analyze once. Reuse context everywhere. A CLI that maps your codebase for developers and AI agents: entry points, critical files, features and routes.
Documentation · Website · GitHub
Every new AI chat about your code starts from zero — you re-explain the same codebase every time. DevMap fixes that.
It's a CLI that combines static analysis with optional AI
interpretation to build a structured, reusable understanding layer
of your project — once. That layer (.devmap/index.json, feature
maps, DEVMAP.md) is what you and any AI agent read afterward,
instead of re-scanning or re-pasting the whole repo. Full repo
source stays local — nothing gets sent wholesale to the AI model.
Install
npm install --global @flaid/devmap
Or run without a global install:
npx @flaid/devmap --help
Requirements
- Node.js 22.12 or newer
- An API key for an AI provider: Groq, OpenRouter, or any custom OpenAI-compatible endpoint
Static analysis still works when AI is not configured.
Quick Start
Run these commands from the root of the project you want to understand:
devmap init
devmap analyze
devmap onboarding
devmap doctor
devmap init selects a provider, validates its key, stores configuration locally, prepares
.devmap/, generates DEVMAP.md, and integrates with AGENTS.md safely.
AI Provider Setup
Choose Groq, OpenRouter, or a custom OpenAI-compatible endpoint with the arrow keys during:
devmap init
Groq keys are available at https://console.groq.com/keys. OpenRouter keys are available at https://openrouter.ai/keys.
For custom endpoints, DevMap asks for the base URL (prefilled with
http://localhost:20128/v1) and lists the models your server exposes, so any
OpenAI-compatible self-hosted gateway works out of the box.
For OpenRouter, DevMap prompts:
OpenRouter model [openrouter/free]:
Press Enter to use the free router, or type any free or paid OpenRouter model ID. The selected model is saved and used as the primary choice.
For non-interactive Groq setup:
GROQ_API_KEY="your-key" devmap init
On PowerShell:
$env:GROQ_API_KEY="your-key"
devmap init
Remove-Item Env:GROQ_API_KEY
For non-interactive OpenRouter setup:
OPENROUTER_API_KEY="your-key" devmap init
The key is stored locally in ~/.devmap/config.json. Requests go directly from
your machine to the selected provider. DevMap does not send the key to a
DevMap-owned server.
Commands
devmap init
devmap analyze
devmap analyze --fresh
devmap map # full project map
devmap map <feature-or-file> # scoped to one feature or file
devmap flow # curated top flows
devmap flow <feature-or-route>
devmap explain <target> # file, feature, or function
devmap onboarding --write
devmap onboarding --write --language id
devmap doctor
devmap config model auto
devmap mcp # run as an MCP server
Groq and OpenRouter use the model selected during init. Change either provider's model with:
devmap config model <model-id>
devmap config model auto
MCP Server
devmap mcp runs DevMap as a Model Context Protocol
server over stdio. An AI agent asks the project map questions with tool calls and
gets structured JSON back, instead of reading a whole context file up front.
devmap analyze
claude mcp add devmap -- npx -y @flaid/devmap mcp
Other clients launch the same command (npx -y @flaid/devmap mcp) as a stdio server:
{
"mcpServers": {
"devmap": {
"command": "npx",
"args": ["-y", "@flaid/devmap", "mcp"]
}
}
}
Tools: devmap_overview, devmap_map, devmap_flow, devmap_routes,
devmap_impact, devmap_find, devmap_analyze and, only with --allow-ai,
devmap_explain.
The server is read-only and static by default: no AI provider is contacted unless
you start it with --allow-ai, and it only writes inside .devmap/ when the agent
calls devmap_analyze or you start it with --auto-refresh. Every answer reports
whether the snapshot is stale. See the
MCP guide for client
setup and tool inputs.
Generated Context
DevMap generates:
.devmap/index.jsonfor lightweight AI-agent navigation.devmap/features/*.jsonfor focused feature maps and source priority.devmap/snapshot.jsonfor the full structured project analysis archiveDEVMAP.mdfor human and AI-agent usage guidance- a small DevMap block in
AGENTS.mdonly after confirmation when the file already exists
Existing AGENTS.md and DEVMAP.md files are never overwritten.
For AI Agents
Read .devmap/index.json first, open the relevant feature map, and inspect its
sourcePriority files. Use .devmap/snapshot.json only when the lightweight
navigation layer is insufficient.
Use --json for scripts, editors, CI, or AI agents:
devmap analyze --json
devmap onboarding --json
devmap doctor --json
JSON mode writes one parseable JSON document to stdout without ANSI colors, terminal decoration, or streamed partial output.
Supported Stacks
- Frontend: Next.js, Astro, SvelteKit, Nuxt, Remix, React Router v7, TanStack Router/Start, Expo Router, SolidStart, Qwik City, Angular, React, Vue, Svelte
- Backend: Express, NestJS, Fastify, Hono, Elysia, Koa, AdonisJS
Detection covers the full list above; Next.js and Express receive the deepest analysis. Multi-package workspaces are classified per project type, so a monorepo containing a CLI and a web app is reported as both.
Privacy
- Project analysis runs locally before AI interpretation.
- Full repository source is not sent to the selected provider.
.envfiles and common generated directories are ignored.- API keys are stored locally and should never be committed.
Links
- Repository: https://github.com/itsflaid/devmap
- Issues: https://github.com/itsflaid/devmap/issues
- Changelog: https://github.com/itsflaid/devmap/blob/main/CHANGELOG.md
License
MIT
devmap MCP questions
How do I add devmap MCP to Claude Code?
Run claude mcp add devmap -- npx -y @flaid/devmap in your terminal. Add --scope user to make it available in every project.
How do I add devmap MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does DevMap send my entire codebase to an AI provider?
No, the full repository source stays local and is not sent wholesale to the AI model.
What AI providers are supported?
DevMap supports Groq, OpenRouter, or any custom OpenAI-compatible endpoint.
Can I use DevMap without an AI provider?
Yes, static analysis still works even if an AI is not configured.