Magpie Search runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from pypi. Last commit 10 Sep 2026.
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
What the code does
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.
r = subprocess.run([str(vmrun), "list"], capture_output=True, text=True, timeout=30, env=safe_env())
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 magpie-search -- uvx magpie-search{
"mcpServers": {
"magpie-search": {
"args": [
"magpie-search"
],
"command": "uvx"
}
}
}[mcp_servers.magpie-search]
command = "uvx"
args = ["magpie-search"]{
"mcpServers": {
"magpie-search": {
"args": [
"magpie-search"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"magpie-search": {
"args": [
"magpie-search"
],
"command": "uvx"
}
}
}Alternatives to Magpie Search
same job, measured the same wayPersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
Rip YouTube transcripts to disk for AI agents, RAG pipelines, and LLM workflows.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Magpie Search — questions
Answers built from our own checks of this server.