NEAT runs on your own machine — the client starts it, so there is no endpoint to ping. 1 757 installs a week from npm. Last commit 17 Sep 2026.
Fused graph of your codebase — static code + runtime OTel — for AI agents, over MCP.
We read the source, 18 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(binary, [arg], { stdio: 'ignore' })
const abs = path.join(serviceDir, candidate)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 neat -- npx -y @neat.is/mcp
{
"mcpServers": {
"neat": {
"args": [
"-y",
"@neat.is/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.neat]
command = "npx"
args = ["-y", "@neat.is/mcp"]
{
"mcpServers": {
"neat": {
"args": [
"-y",
"@neat.is/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"neat": {
"args": [
"-y",
"@neat.is/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
NEAT_CORE_URL (URL of the NEAT daemon the server queries. Defaults to the local daemon.).
The author declared them in the registry entry; get the values from the project itself.
Semantic code graph MCP server for coding agents
Local file search for AI agents — semantic + keyword indexing over your codebase.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Content-addressed code graph with 22 MCP tools for AI agents.
Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents.
Local-first codebase intelligence MCP server for AI coding agents.
MCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep.
Evidence-traced codebase understanding and security scanning for AI agents over MCP.
Answers built from our own checks of this server.