Dixa MCP Server
A FastMCP server implementation for the Dixa API, providing resources and tools for managing conversations and tags.
Features
Resources
- Search conversations
- Get conversation details
- Get conversation notes
- Get conversation messages
- Get available tags
Tools
- Add tags to conversations
- Remove tags from conversations
Project Structure
/src
├── dixa.ts # Main server setup
├── config.ts # Configuration and environment settings
├── types.ts # Shared types and error handling
├── resources/ # Resource implementations
├── schemas/ # Zod schemas for validation
└── tools/ # Tool implementations
Configuration
The server requires the following environment variables:
DIXA_API_KEY
: Your Dixa API keyDIXA_API_BASE_URL
(optional): Override the default API URL (defaults to ‘https://dev.dixa.io/v1’)
Usage
- Set up environment variables:
export DIXA_API_KEY='your-api-key'
- Start the server:
npm start
## Running Your Server
### Test with `mcp-cli`
The fastest way to test and debug your server is with `fastmcp dev`:
```bash
npx fastmcp dev server.js
npx fastmcp dev server.ts
This will run your server with mcp-cli
for testing and debugging your MCP server in the terminal.
Inspect with MCP Inspector
Another way is to use the official MCP Inspector
to inspect your server with a Web UI:
npx fastmcp inspect server.ts
FAQ
How to use with Claude Desktop?
Follow the guide https://modelcontextprotocol.io/quickstart/user and add the following configuration:
{
"mcpServers": {
"my-mcp-server": {
"command": "npx",
"args": [
"tsx",
"/PATH/TO/YOUR_PROJECT/src/index.ts"
],
"env": {
"YOUR_ENV_VAR": "value"
}
}
}
}
Development
Adding a New Resource
- Create a schema in
src/schemas/
- Create the resource in
src/resources/
- Add the resource to
src/dixa.ts
Example resource:
export const myResource = {
uri: "dixa://my-resource",
name: "My Resource",
description: "Description",
load: async (args: MyArgs, apiKey: string) => {
// Implementation
}
};
Adding a New Tool
- Create the tool in
src/tools/
- Add the tool to
src/dixa.ts
Example tool:
export const myTool = {
name: "My Tool",
description: "Description",
execute: async (args: MyArgs, apiKey: string) => {
// Implementation
}
};
Error Handling
The project uses custom error classes:
DixaError
: Base error class for API errorsDixaValidationError
: For response validation failures
Showcase
[!NOTE]
If you’ve developed a server using FastMCP, please submit a PR to showcase it here!
- https://github.com/apinetwork/piapi-mcp-server
- https://github.com/Meeting-Baas/meeting-mcp - Meeting BaaS MCP server that enables AI assistants to create meeting bots, search transcripts, and manage recording data
Acknowledgements
- FastMCP is inspired by the Python implementation by Jonathan Lowin.
- Parts of codebase were adopted from LiteMCP.
- Parts of codebase were adopted from Model Context protocolでSSEをやってみる.
Contributing
- Follow the existing patterns for resources and tools
- Add proper JSDoc documentation
- Use the shared utilities in
types.ts
andconfig.ts
- Update the README if adding new features
Dixa MCP Server
Project Details
- ktabori/dixa-mcp
- MIT License
- Last Updated: 3/26/2025
Recomended MCP Servers
MCP server that provides direct access to MySQL databases
Model Context Protocol Servers for Azure AI Search
This read-only MCP Server allows you to connect to Trello data from Claude Desktop through CData JDBC Drivers....
Official Vectorize MCP Server
MRP (materials requirement planning) MCP which can extract data necessary for making an MRP calculation and make the...
Flow blockchain tools for Model Context Protocol (MCP)
A powerful personal assistant server that integrates with various services including Google Calendar, Obsidian Vault, Trello, and web...
This is an implementation project of a JVM-based MCP (Model Context Protocol) server. The project aims to provide...