AsterMind MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 51 installs a week from npm. Last commit 25 Sep 2026.
On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.
Today is the operative word: we check AsterMind 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 astermind-mcp -- npx -y @astermind/astermind-mcp
{
"mcpServers": {
"astermind-mcp": {
"command": "npx",
"args": [
"-y",
"@astermind/astermind-mcp"
]
}
}
}
[mcp_servers.astermind-mcp]
command = "npx"
args = ["-y", "@astermind/astermind-mcp"]
{
"mcpServers": {
"astermind-mcp": {
"command": "npx",
"args": [
"-y",
"@astermind/astermind-mcp"
]
}
}
}
{
"servers": {
"astermind-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@astermind/astermind-mcp"
]
}
}
}
Apple developer docs and WWDC transcripts with RAG retrieval and Jev relevance ranking.
Protected RAG storage — agents discover public metadata, content only by access token.
MCP server that converts raster images (PNG/JPG/WEBP) to SVG vector format
Text extraction, keyword extraction, language detection, and chunking for RAG
Text extraction, keyword extraction, language detection, and chunking for RAG
RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Answers built from our own checks of this server.