Cgraphy runs on your own machine — the client starts it, so there is no endpoint to ping. 63 installs a week from pypi. Last commit 18 Jul 2026.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
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.
этот файл ставится пользователю, но в репозитории его нет
out = subprocess.run(
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 cgraphy -- uvx cgraphy
{
"mcpServers": {
"cgraphy": {
"args": [
"cgraphy"
],
"command": "uvx"
}
}
}
[mcp_servers.cgraphy]
command = "uvx"
args = ["cgraphy"]
{
"mcpServers": {
"cgraphy": {
"args": [
"cgraphy"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"cgraphy": {
"args": [
"cgraphy"
],
"command": "uvx"
}
}
}
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Token-bounded repository context for coding agents over MCP.
Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster
Semantic code graph MCP server for coding agents
Codebase knowledge graph — architectural awareness for AI coding agents via MCP
Content-addressed code graph with 22 MCP tools for AI agents.
Context-aware code retrieval MCP server — ranked, gated results for AI coding agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Answers built from our own checks of this server.