Embgrep runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from pypi. Last commit 15 Apr 2026.
Local semantic search — embedding-powered grep for files, zero external services.
Today is the operative word: we check Embgrep 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 embgrep -- uvx embgrep
{
"mcpServers": {
"embgrep": {
"args": [
"embgrep"
],
"command": "uvx"
}
}
}
[mcp_servers.embgrep]
command = "uvx"
args = ["embgrep"]
{
"mcpServers": {
"embgrep": {
"args": [
"embgrep"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"embgrep": {
"args": [
"embgrep"
],
"command": "uvx"
}
}
}
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Bilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
MCP server for the xAI Grok API — chat, vision, search, and embeddings
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Answers built from our own checks of this server.