NervaPack runs on your own machine — the client starts it, so there is no endpoint to ping. 696 installs a week from pypi. Last commit 24 Aug 2026.
Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.
We read the source, 19 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.
result = subprocess.run(
os.path.join(
self.DOWNLOAD_PATH, self.EXTRACTED_FOLDER_NAME, "model.onnx"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 nervapack -- uvx nervapack
{
"mcpServers": {
"nervapack": {
"args": [
"nervapack"
],
"command": "uvx"
}
}
}
[mcp_servers.nervapack]
command = "uvx"
args = ["nervapack"]
{
"mcpServers": {
"nervapack": {
"args": [
"nervapack"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"nervapack": {
"args": [
"nervapack"
],
"command": "uvx"
}
}
}
Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Agent runtime with typed memory, knowledge and code graphs, plus file and web tools
Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions
FAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline.
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
Answers built from our own checks of this server.