Codemesh runs on your own machine — the client starts it, so there is no endpoint to ping. 30 installs a week from npm. Last commit 20 Apr 2026.
Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster
Today is the operative word: we check Codemesh every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add codemesh -- npx -y @pyalwin/codemesh
{
"mcpServers": {
"codemesh": {
"args": [
"-y",
"@pyalwin/codemesh"
],
"command": "npx"
}
}
}
[mcp_servers.codemesh]
command = "npx"
args = ["-y", "@pyalwin/codemesh"]
{
"mcpServers": {
"codemesh": {
"args": [
"-y",
"@pyalwin/codemesh"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"codemesh": {
"args": [
"-y",
"@pyalwin/codemesh"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
CODEMESH_PROJECT_ROOT (Absolute path to the local codebase to index).
The author declared them in the registry entry; get the values from the project itself.
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Code Intelligence Platform for AI Coding Agents
Graph-powered code intelligence with semantic search and knowledge graph for AI assistants
Persistent, evidence-backed code graph for coding agents.
Cross-repository semantic code intelligence for AI coding agents, from a local code graph.
Local code-memory graph for AI coding agents.
Codebase knowledge graph — architectural awareness for AI coding agents via MCP
Answers built from our own checks of this server.