What environment variables are required?
`API_BASE_URL` is required; optionally set `SERVER_NAME`, `SERVER_VERSION`, and `DEBUG` (default false) in your `.env` file.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"elijahdev0_mcp-server": {
"command": "node",
"args": [
"server.js"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An MCP (Model Context Protocol) server that provides a standardized interface to the Letta API, enabling AI agents to manage tools, sources, and agents through MCP-compatible consumers like Claude.js.
Install dependencies with npm install, copy .env.example to .env, configure the required API_BASE_URL and authorization details, then run npm start or npm run start:ts. Connect from any MCP-compatible client using stdin/stdout transport.
`API_BASE_URL` is required; optionally set `SERVER_NAME`, `SERVER_VERSION`, and `DEBUG` (default false) in your `.env` file.
Use `npm start` for the JavaScript version or `npm run start:ts` for TypeScript (compiles on the fly). Alternatively, build with `npm run build` and run `node dist/server.js`.
It provides tools for tools (CRUD, Composio, MCP server management), sources (CRUD, file operations), and agents (list, create, export, import). Each tool corresponds to a Letta API endpoint.
Use a MCP-compatible client (e.g., Claude.js) with a stdin/stdout transport pointing to the server command. Example: `createStdio({ command: "node path/to/server.js" })`.
Authorization details are configured in the `.env` file (authorization headers are included in API requests), but the README does not specify the exact authentication method.
Hindsight: Agent Memory That Learns

LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
Comments