MCPLow riskUnclaimed

neuronscope

Traces which neurons and attention heads drive a language model's output via MCP tools.

RudrenduPaulrudrendupaul/neuronscope★ 1Updated Aug 11, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.RudrenduPaul/neuronscope",
  "description": "Traces which neurons and attention heads drive a language model's output via MCP tools.",
  "repository": {
    "url": "https://github.com/RudrenduPaul/NeuronScope",
    "source": "github"
  },
  "version": "0.1.5",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "neuronscope-cli",
      "version": "0.1.5",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "runtimeArguments": [
        {
          "value": "neuronscope-cli",
          "type": "named",
          "name": "--from"
        }
      ],
      "packageArguments": [
        {
          "value": "neuronscope-mcp",
          "type": "positional",
          "valueHint": "script_name"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:neuronscope-cli@0.1.5
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.5latestOct 7, 2026