Skip to content
MCP server

naja-scope

Query elaborated SystemVerilog, Verilog and VHDL designs without pasting source

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI
Runs
Locally
Version
0.1.26
Listing updated
2 days ago

About naja-scope

naja-scope is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

The point is to answer structural questions from the elaborated design instead of from text search. The agent asks what drives a signal, what a module contains or where a net originates, and gets small answers with file-and-line references. It is built on the najaeda netlist engine and also reads gate-level netlists loaded with a Liberty library.

The README's benchmark used 17 questions on the CVA6 core: the same Claude Code agent scored 17/17 with naja-scope and 10/17 with grep and file reading, in 77 turns instead of 123. Elaborated-hierarchy questions were where source search failed.

Responses are token-bounded with pagination and truncation markers. It runs over stdio, or over HTTP for ChatGPT, where the README warns there is no built-in authentication.

Install

Run in a terminal

claude mcp add naja-scope -- uvx naja-scope

Add to claude_desktop_config.json

{
  "mcpServers": {
    "naja-scope": {
      "command": "uvx",
      "args": [
        "naja-scope"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "naja-scope": {
      "command": "uvx",
      "args": [
        "naja-scope"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "naja-scope": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "naja-scope"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "naja-scope": {
      "command": "uvx",
      "args": [
        "naja-scope"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "naja-scope": {
      "command": "uvx",
      "args": [
        "naja-scope"
      ]
    }
  }
}

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

get_module_card
Summarizes a module, including register bits, memories and cell counts.
get_source
Shows the source line of a cell or net.

What it does

Connectivity tracing
Finds drivers and loads of any signal across modules.
Hierarchy walking
Explores modules, instances and ports on demand.
Logic cones
Traces combinational cones up to the register boundary.
Source references
Every answer carries file and line ranges.
Gate-level support
Loads netlists with Liberty cell libraries.

Good for

  • Trace what drives an output port
  • Count elaborated variants of a module
  • Inspect register groups under a stage
  • Read gate-level netlist cells

Pricing

Open source

Open-source; free to install from PyPI.

naja-scope FAQ

How do I install it?

Run it with uvx naja-scope or pip install naja-scope.

Does it support VHDL?

Yes, marked beta.

Can ChatGPT use it?

Yes, over streamable HTTP, but there is no built-in auth so use a trusted tunnel.

What version of najaeda is needed?

0.7.35 or newer.

Is naja-scope free?

Yes. naja-scope is open source, so you can use and self-host it for free.

How do I add naja-scope to Claude Code?

Run this command in your terminal: claude mcp add naja-scope -- uvx naja-scope

What are the best alternatives to naja-scope?

The closest alternatives to naja-scope are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to naja-scope

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools