Neuronpedia MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_explanationC | Generate an explanation for a specific feature in an AI model |
| search_explanationsB | Search for explanations across models and layers |
| get_activationsB | Get activation values for a specific feature on given text |
| search_top_featuresC | Find the top activating features for given text |
| steer_generationC | Steer model generation using a specific feature |
| create_vectorB | Create a custom vector for steering |
| list_vectorsA | List all custom vectors |
| get_vectorB | Get a specific vector by ID |
| delete_vectorB | Delete a vector by ID |
| generate_attribution_graph | Generate an attribution graph for analyzing text prompts |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
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.
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.
With 9 tools, the set is well-scoped for a focused domain like neuronpedia. It covers essential operations without being too sparse or overwhelming.
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.