@lamatic/mcp
Unified MCP server combining dev, graph, docs, and kit tools for Lamatic.ai. Enables managing orgs/projects/flows, executing flows, querying docs via RAG, and browsing AgentKit contributions.
README
@lamatic/mcp
Unified Lamatic MCP server. Merges @lamatic/dev-mcp, @lamatic/graph-mcp, a proxy to the hosted Lamatic Docs MCP, and kit_* — the AgentKit MCP — into one server.
Install
npx @lamatic/mcp
Setup
Claude Desktop / Cursor / Claude Code
{
"mcpServers": {
"lamatic": {
"command": "npx",
"args": ["-y", "@lamatic/mcp"]
}
}
}
For GraphMCP's execution-only mode (no org key, single flow — e.g. the Studio "Connect with AI" snippet), add env vars instead:
{
"mcpServers": {
"lamatic": {
"command": "npx",
"args": ["-y", "@lamatic/mcp"],
"env": {
"PROJECT_API_KEY": "<projectApiKey>",
"PROJECT_ID": "<projectId>",
"ENDPOINT": "<endpoint>",
"FLOW_ID": "<flowId>"
}
}
}
}
For kit_* tools that write to GitHub (kit_revalidate_pr), optionally add a token to raise GitHub's API rate limit and enable posting /validate comments:
{
"mcpServers": {
"lamatic": {
"command": "npx",
"args": ["-y", "@lamatic/mcp"],
"env": {
"GITHUB_TOKEN": "<github-personal-access-token>"
}
}
}
}
Tool prefixes
| Prefix | Covers | Auth |
|---|---|---|
dev_* |
Org/project/flow/credential management | dev_auth_login, or LAMATIC_API_KEY + LAMATIC_ORG_ID env vars |
graph_* |
Execute deployed flows | graph_auth_login (full mode), or PROJECT_API_KEY/PROJECT_ID/ENDPOINT env vars (execution-only mode) |
docs_* |
Query Lamatic.ai docs via RAG | none — proxies to the public hosted endpoint |
kit_* |
Browse, search, and validate AgentKit contributions | none for read/validate tools; GitHub token (kit_auth_login or GITHUB_TOKEN env var) only for kit_revalidate_pr |
Config
All credentials live in one namespaced file: ~/.lamatic/config.json
{
"dev": { "apiKey": "...", "orgId": "...", "userId": "..." },
"graph": { "orgApiKey": "...", "projectApiKey": "...", "orgId": "..." },
"kit": { "githubToken": "..." }
}
Each namespace degrades independently — missing dev credentials only break dev_* tools, not graph_*, docs_*, or kit_*.
Architecture notes
docs_*does not duplicate the RAG-calling logic from the Lamatic-MCP-Docs repo. It runs a thin MCP client (utils/docsProxy.js) that connects to the existing hosted endpoint (https://docmcp.lamatic.ai/api/mcp) and forwards the call. The standalone hosted endpoint keeps working unchanged for zero-install users.kit_*reads directly from the publicLamatic/AgentKitGitHub repo viautils/kitProxy.js— there is no hosted Kit API today. If one ever gets stood up (the same waydocs_*proxies to a hosted endpoint instead of calling GitHub/RAG directly), the fetch calls inkitProxy.jsare the only thing that needs to change; tool signatures intools/kit.jsstay the same.kit_validate_structuremirrors the Phase 1 checks invalidate-pr.ymlby hand. There's no CI link between the two files today — if Phase 1's bash logic changes, this needs a matching manual update or the two will silently disagree on what counts as a valid kit.
Local development
git clone <this-repo>
cd lamatic-mcp
npm install
node server.js
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.