Neuronpedia MCP Server
by manncodes
README.md
# Neuronpedia MCP Server
A Model Context Protocol (MCP) server that provides access to the Neuronpedia API for AI model interpretability and feature analysis.
## Features
- **Explanations**: Generate and search explanations for AI model features
- **Activations**: Analyze feature activations on specific text inputs
- **Steering**: Control model generation using specific features
- **Vectors**: Create and manage custom steering vectors
## Installation
```bash
npm install
npm run build
```
## Configuration
Set your Neuronpedia API key as an environment variable:
```bash
export NEURONPEDIA_API_KEY=your_api_key_here
```
You can obtain your API key by logging in at [neuronpedia.org](https://neuronpedia.org) and visiting your account page.
## Usage
### Running the server
```bash
npm start
```
### Available Tools
1. **generate_explanation** - Generate explanations for model features
2. **search_explanations** - Search existing explanations
3. **get_activations** - Get feature activations for text
4. **search_top_features** - Find top activating features
5. **steer_generation** - Steer model generation with features
6. **create_vector** - Create custom steering vectors
7. **list_vectors** - List all vectors
8. **get_vector** - Get specific vector
9. **delete_vector** - Delete a vector
### MCP Client Configuration
Add this to your MCP client configuration:
```json
{
"mcpServers": {
"neuronpedia": {
"command": "node",
"args": ["/path/to/neuronpedia-mcp/dist/index.js"],
"env": {
"NEURONPEDIA_API_KEY": "your_api_key"
}
}
}
}
```
## Development
```bash
npm run dev
```
## License
MITTDQS
A3.7/5.0
Scored across 9 tools
Disambiguation5/5
Each tool targets a distinct operation: explanation generation/search, activation retrieval, feature search, steering, and vector management. No two tools have overlapping purposes, ensuring clear disambiguation.
Naming Consistency5/5
All tool names follow a consistent snake_case verb_noun pattern (e.g., generate_explanation, list_vectors, delete_vector), making the set predictable and easy to navigate.
Tool Count5/5
With 9 tools, the set is well-scoped for a focused domain like neuronpedia. It covers essential operations without being too sparse or overwhelming.
Completeness5/5
The tool surface provides a complete workflow: explanation generation and search, activation analysis, feature search, steering via vectors, and full CRUD for custom vectors. No obvious gaps.
Maintenance
ActivityInactive
ResponsivenessNo issues