VFB3

Provides access to VirtualFlyBrain data via HTTP and local MCP endpoints for querying terms, running queries, and searching VFB data.
  • typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can access VFB3-MCP to query VirtualFlyBrain data, run predefined queries, and search for terms using a standard MCP client. This server exposes a hosted HTTP endpoint for immediate use and also supports local, serverless development workflows so you can run the MCP server on your machine and connect your clients to it.

How to use

Choose an MCP client you prefer and connect to one of the available endpoints. For the live service, use the hosted HTTP URL to query VFB data, run queries, and search terms without any setup.

If you prefer running the MCP server locally, start a local process that exposes the MCP over a stdio or HTTP endpoint, then configure your MCP client to point at the local server. The local setups described below provide explicit commands to start the server on your machine.

Common usage patterns include retrieving detailed information about a specific VFB term, running predefined queries such as PaintedDomains for a given term, and performing term searches against the VFB Solr index. Use the HTTP endpoint for remote access or the local stdio configuration to run the server directly from your environment.

How to install

Prerequisites include Node.js 18 or higher and npm or yarn. If you will run the server locally, install dependencies, build, and start the server according to the steps below.

Clone the repository, install dependencies, build, and start the server locally using the commands shown.

git clone https://github.com/Robbie1977/VFB3-MCP.git
cd VFB3-MCP
npm install
npm run build
npm start

Configuration and local development endpoints

HTTP live service endpoint you can use immediately from any MCP client is the hosted URL below.

To run locally, use the following command to start the MCP server as a local node process. This starts the server from the built distribution.

{
  "mcpServers": {
    "vfb3-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/VFB3-MCP/dist/index.js"]
    }
  }
}

Testing the connection

After configuring your MCP client, verify connectivity by issuing queries such as retrieving information for a term, running a PaintedDomains query for a known VFB ID, or searching terms like medulla. Successful responses indicate the setup is complete and the MCP server is ready.

Available tools and capabilities

This server exposes a set of tools to access VFB data programmatically. The core capabilities include retrieving term information, executing predefined queries, and searching terms against the VFB index.

Available tools

get_term_info

Retrieve detailed information about VFB terms using their IDs.

run_query

Execute predefined queries on VFB data using a specified query type.

search_terms

Search for VFB terms using the Solr search server.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational