MCP.Market

NervaPack MCP server

by ramdhavepreetam·io.github.ramdhavepreetam/nervapack·v0.5.8·1 stars
No reviews yet

Offline codebase knowledge graph: 91% token reduction vs naive RAG, plus cross-session agent memory.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed NervaPack yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

NervaPack tools (21)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • explore

    List entities (classes, functions, imports) in the knowledge graph.

  • graph_status

    Return the current state of the NervaPack knowledge graph.

  • impact

    Perform impact analysis (reverse dependency search).

  • memory_about

    Return all current memories linked to a named entity.

  • memory_clear_session

    Tombstone or hard-purge all nodes belonging to a session.

  • memory_end_session

    Close the current session with an outcome summary and queue consolidation.

  • memory_for_code

    Return memories that TOUCH a given source file, optionally at a specific line.

  • memory_forget

    Tombstone (soft-delete) or hard-purge memory nodes.

  • memory_import

    Bulk-seed memory from a list of node specs.

  • memory_list_sessions

    List all sessions with node counts, newest first.

  • memory_recall

    Retrieve the most relevant memories for a query within a token budget.

  • memory_start_session

    Open a named session. Returns the session ID and whether it was newly created.

  • memory_stats

    Return node counts by kind, DB size, top entities by degree, and all namespaces.

  • memory_store

    Persist a new memory node.

  • memory_switch_namespace

    Switch the active namespace. Resets the active session.

  • memory_timeline

    Chronological trace of all memories matching a topic, including superseded ones.

  • memory_to_code

    Return code locations (file + line range) that a memory node TOUCHES.

  • memory_verify

    Confirm or refute a memory node, adjusting its confidence.

  • memory_verify_staleness

    Scan TOUCHES edges and flag memories whose source file changed since they were stored.

  • memory_why

    Explain a decision: show rationale, rejected alternatives, and caused outcomes.

  • query

    Query the NervaPack knowledge graph for relevant code context.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan42 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 33 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How NervaPack compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 4,460 AI and agents servers
Tools
21
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,711 AI and agents servers

What its tools let an agent do: 21 read

Install NervaPack in Claude Code, Cursor or VS Code

claude mcp add nervapack -- uvx nervapack
Add to Cursor

What the publisher says

From the NervaPack repository's README, as published. We do not edit it. Read it on GitHub

NervaPack

<!-- mcp-name: io.github.ramdhavepreetam/nervapack -->

NervaPack is a privacy-first, offline knowledge graph for your codebase. It solves two fundamental problems with standard Vector RAG:

  • Token waste — chunk-based RAG retrieves blobs of text that may only tangentially relate to your query, bloating your context window.
  • Privacy risk — sending code to cloud embedding APIs leaks your proprietary logic.

NervaPack runs 100% on your machine. It uses tree-sitter to parse your codebase into a deterministic Abstract Syntax Tree graph, then uses a local Ollama model to draw hard semantic edges between your documentation and your code. Queries traverse this graph with a K-Hop BFS, returning a hyper-targeted, token-efficient context window — no cloud required.

Verified Performance

91.2% Average Token Reduction — independently verified on real-world codebases.

Cost Savings: $181–$724 per developer per year (GPT-4o to Claude Sonnet)

📊 View Full Benchmarks · 🧪 Messy Code Performance

Code quality impact: 90–99% reduction on clean code, 50–75% on legacy/messy code. Even poorly structured codebases benefit significantly.

Why NervaPack vs. standard Vector RAG

Prerequisites

  • Python 3.10+
  • Git — your project must be a git repository (git init if not)

(Optional for semantic code-doc binding) — an LLM provider. Structural graph indexing and basic queries work out-of-the-box with zero configuration and no cloud connection.

Installation

# Recommended
pip install nervapack

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

NervaPack: common questions

Is NervaPack MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the NervaPack safety report
How do I install NervaPack?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does NervaPack need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is NervaPack maintained?
The last commit was 72 days ago (2026-08-24). The latest release is v0.5.8.
What can I use instead of NervaPack?
Servers from other publishers that do the same job: Total Agent Memory MCP server, Basic Memory MCP server and IWE (iwe.md) MCP server.
How does NervaPack compare with other AI and agents MCP servers?
safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 21 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to NervaPack

Same job from other publishers: the closest match first, then the best rated.

  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • MCP AutoMem
    Graph-vector memory for AI assistants using FalkorDB and Qdrant
    C
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A