Graphlens MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 134 installs a week from pypi. Last commit 3 Jul 2026.
Semantic code graph MCP server for coding agents
Today is the operative word: we check Graphlens 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 graphlens-mcp -- uvx graphlens-mcp
{
"mcpServers": {
"graphlens-mcp": {
"command": "uvx",
"args": [
"graphlens-mcp"
]
}
}
}
[mcp_servers.graphlens-mcp]
command = "uvx"
args = ["graphlens-mcp"]
{
"mcpServers": {
"graphlens-mcp": {
"command": "uvx",
"args": [
"graphlens-mcp"
]
}
}
}
{
"servers": {
"graphlens-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"graphlens-mcp"
]
}
}
}
Hybrid semantic and keyword code search for coding agents.
Semantic code graph for AI-assisted code understanding via tree-sitter and MCP.
Local-first codebase intelligence MCP server for AI coding agents.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Local code graph and solution memory for coding agents via CLI and MCP.
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
Zero-LLM structural code retrieval for AI coding agents, served over MCP.
Context-aware code retrieval MCP server — ranked, gated results for AI coding agents
Answers built from our own checks of this server.