Tokennuke runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from pypi. Last commit 2 Mar 2026.
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
Today is the operative word: we check Tokennuke 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 tokennuke -- uvx tokennuke
{
"mcpServers": {
"tokennuke": {
"args": [
"tokennuke"
],
"command": "uvx"
}
}
}
[mcp_servers.tokennuke]
command = "uvx"
args = ["tokennuke"]
{
"mcpServers": {
"tokennuke": {
"args": [
"tokennuke"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"tokennuke": {
"args": [
"tokennuke"
],
"command": "uvx"
}
}
}
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Code intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP tools.
The open retrieval layer for AI agents — index code, docs, data. Search via MCP.
LynxMCP: 100% local MCP server for the code questions grep can't answer: call graph, hybrid search
Semantic code retrieval engine with hybrid search, context expansion, and 40+ language support.
Code intelligence MCP: symbols, call graphs, change impact + affected tests, routes, search.
AST-based semantic code search: 33 tools, 35 languages, call tracing, impact analysis
Answers built from our own checks of this server.