- Letta MCP Server
created by
oculairmedia14 hours ago
MCP server to manage letta server and comunicate with agents
Information
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 and manage memory blocks
- Attach memory blocks to agents
- 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 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 blocklist_memory_blocks
: List all memory blocksattach_memory_block
: Attach a memory block to an agent
Tool Management
list_tools
: List all available toolslist_agent_tools
: List tools available for a specific agentattach_tool
: Attach a tool to an agent
Example Usage
When integrated with Cline, you can use the MCP tools as follows:
// 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."
}
</arguments>
</use_mcp_tool>
// Attach the block to an agent
<use_mcp_tool>
<server_name>letta</server_name>
<tool_name>attach_memory_block</tool_name>
<arguments>
{
"block_id": "returned_block_id",
"agent_id": "target_agent_id"
}
</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
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers

MongoDB LensFull featured MCP Server for MongoDB database analysis.

Mcp Server RagdocsAn MCP server that provides tools for retrieving and processing documentation through vector search, both locally or hosted. Enabling AI assistants to augment their responses with relevant documentation context.
Most Popular Model Context Protocol (MCP) ServersA curated list of the most popular Model Context Protocol (MCP) servers based on usage data from Smithery.ai

Microsoft SQL Server MCP Server (MSSQL)MS SQL MCP Server
An easy-to-use bridge that lets AI assistants like Claude directly query and explore Microsoft SQL Server databases. No coding experience required!
What Does This Tool Do?
This tool allows AI assistants to:
Discover tables in your SQL Server database
View table structures (columns, data types, etc.)
Execute read-only SQL queries safely
Generate SQL queries from natural language requests
Template for MCP Server
mcp-deepresearchlocal mcp server perplexity

GithubMCP Server for the GitHub API, enabling file operations, repository management, search functionality, and more.

ChatSumQuery and Summarize your chat messages.
Perplexity Web Search MCP ServerA perplexity MCP server
Nuanced MCP ServerA Model Context Protocol (MCP) server that provides call graph analysis capabilities to LLMs through the nuanced library