Neurarch MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 96 installs a week from npm. Last commit 1 Sep 2026.
Reads your PyTorch .py or Neurarch graph so agents can inspect, lint and cost the model.
Today is the operative word: we check Neurarch MCP 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 neurarch-mcp -- npx -y neurarch-mcp
{
"mcpServers": {
"neurarch-mcp": {
"args": [
"-y",
"neurarch-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.neurarch-mcp]
command = "npx"
args = ["-y", "neurarch-mcp"]
{
"mcpServers": {
"neurarch-mcp": {
"args": [
"-y",
"neurarch-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"neurarch-mcp": {
"args": [
"-y",
"neurarch-mcp"
],
"command": "npx"
}
}
}
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
Search 276,000+ open source icons and insert them as SVG or React components while you code.
Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.
Fused graph of your codebase — static code + runtime OTel — for AI agents, over MCP.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
The static analyzer your AI agent reads — fix-ready, machine-readable scan reports over MCP.
Finds real, maintained open-source repos that fit your project. MCP grounding for coding agents.
Answers built from our own checks of this server.