Letta MCP Server
Mirror of
MCP-Mirror
README
Letta MCP Server
An MCP (Model Context Protocol) server implementation for interacting with the Letta API. This server provides tools for managing agents, memory blocks, and tools in the Letta system.
Features
- Create and manage Letta agents
- List and filter available agents
- Create, read, update, and manage memory blocks
- List memory blocks with filtering and pagination
- Attach memory blocks to agents with custom labels
- List and manage agent tools
- Send messages to agents and receive responses
Installation
# Clone the repository
git clone https://github.com/oculairmedia/Letta-MCP-server.git
cd letta-server
# Install dependencies
npm install
Configuration
- Create a
.env
file in the root directory with the following variables:
LETTA_BASE_URL=your_letta_api_url
LETTA_PASSWORD=your_letta_api_password
You can use the provided .env.example
as a template.
Available Scripts
npm run build
: Build the TypeScript codenpm run start
: Build and start the servernpm run dev
: Start the server in development mode with watch mode enabled
Tools
Agent Configuration
Agents can be configured with various options:
- Model selection (e.g., 'gpt-4', default: 'openai/gpt-4')
- Embedding model (default: 'openai/text-embedding-ada-002')
- Context window size (default: 16000)
- Temperature and token settings
- Custom function configurations
Memory Block Types
Memory blocks serve different purposes based on their labels:
persona
: Define agent personality and behaviorhuman
: Store conversation history and user preferencessystem
: Store system-level instructions and configurationscustom
: User-defined memory blocks for specific use cases
Agent Management
create_agent
: Create a new Letta agent with specified configurationlist_agents
: List all available agents in the Letta systemprompt_agent
: Send a message to an agent and get a response
Memory Block Management
create_memory_block
: Create a new memory block with name, label, and contentread_memory_block
: Get full details of a specific memory blockupdate_memory_block
: Update contents and metadata of a memory blocklist_memory_blocks
: List memory blocks with filtering options:- Filter by name, label, or content
- Filter by agent
- Filter templates only
- Pagination support
- Include full content or previews
attach_memory_block
: Attach a memory block to an agent with custom labels
Tool Management
list_tools
: List all available tools with filtering and paginationlist_agent_tools
: List tools available for a specific agentattach_tool
: Attach a tool to an agentupload_tool
: Upload a new Python tool with:- Custom name and description
- Source code implementation
- Category/tag support
- Optional automatic agent attachment
API Version
This server interacts with version 1 of the Letta API (endpoint: /v1
). The API version is automatically handled by the server based on the configured LETTA_BASE_URL
.
Example Usage
When integrated with Cline, you can use the MCP tools as follows:
Memory Block Operations
// Create a memory block
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>create_memory_block</tool_name>
<arguments>
{
"name": "example_block",
"label": "custom",
"value": "This is an example memory block.",
"metadata": {
"version": "1.0",
"type": "documentation"
}
}
</arguments>
</use_mcp_tool>
// List memory blocks with filtering
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>list_memory_blocks</tool_name>
<arguments>
{
"label": "custom",
"page": 1,
"pageSize": 10,
"include_full_content": true
}
</arguments>
</use_mcp_tool>
// Update a memory block
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>update_memory_block</tool_name>
<arguments>
{
"block_id": "block-123",
"value": "Updated content",
"metadata": {
"version": "1.1"
}
}
</arguments>
</use_mcp_tool>
// Attach block to agent with label
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>attach_memory_block</tool_name>
<arguments>
{
"block_id": "block-123",
"agent_id": "agent-456",
"label": "persona"
}
</arguments>
</use_mcp_tool>
Tool Management
// Upload a new tool
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>upload_tool</tool_name>
<arguments>
{
"name": "weather_tool",
"description": "Get weather information for a location",
"source_code": "def get_weather(location):\n # Tool implementation\n return {'temp': 72, 'condition': 'sunny'}",
"category": "utilities",
"agent_id": "agent-456" // Optional: automatically attach to agent
}
</arguments>
</use_mcp_tool>
// List tools with filtering
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>list_tools</tool_name>
<arguments>
{
"filter": "weather",
"page": 1,
"pageSize": 10
}
</arguments>
</use_mcp_tool>
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Response Format
All MCP tools return responses in a consistent format:
{
"success": boolean,
"message": string, // Success/error message
"error"?: string, // Present only on error
"details"?: any, // Additional error details if available
// Tool-specific data...
}
Error Handling
The server handles various error scenarios:
- Invalid arguments or missing required parameters
- API authentication failures
- Resource not found errors
- Rate limiting and quota errors
- Network connectivity issues
Each error response includes detailed information to help troubleshoot issues.
Performance Considerations
- Memory blocks support pagination to handle large datasets efficiently
- Tool source code is validated before upload
- Streaming support for agent responses to handle long conversations
- Automatic cleanup of old/unused resources
- Request rate limiting to prevent API overload
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Mathematica Documentation MCP server
A server that provides access to Mathematica documentation through FastMCP, enabling users to retrieve function documentation and list package symbols from Wolfram Mathematica.
kb-mcp-server
An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded
Research MCP Server
The server functions as an MCP server to interact with Notion for retrieving and creating survey data, integrating with the Claude Desktop Client for conducting and reviewing surveys.