O
oculairmedia/Letta-MCP-server
Manage a Letta server and talk to its agents
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项(本地服务器用 command + args,示例见 客户端接法) - 重启客户端
取自该仓库的安装命令
npm install -g letta-mcp-server
解析自我们于 2026-11-05 抓取的该仓库 README;我们未执行过。
这条是仓库自己写的安装方式,不是 MCP 客户端配置,所以不生成 JSON。
配置项的键名以你的客户端为准:客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
- 收录与活跃
- 收录于 2026-11-05 · 最近见到 2026-11-14 · 共见到 10 次 · 被 10 个来源列出
- 评分构成
- 综合分 1,003 · 10 个来源 · mcp
- 安装
npm install -g letta-mcp-server
常见问题(答案都来自我们的记录)
怎么安装?
该仓库给出的安装命令是
npm install -g letta-mcp-server。我们的记录里它是仓库自己提供的;不保证在你的客户端上直接可用。它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
我们收录于 2026-11-05;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# Letta MCP Server
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
A high-performance Model Context Protocol (MCP) server for Letta AI, built with Rust and the TurboMCP framework.
## Features
7 Consolidated Tools covering 103 operations using the discriminator pattern
High Performance -- Rust, ~10-30MB memory, <500ms startup, parallel fan-out via tokio::join! and bufferunordered
Dual Transport -- stdio (Claude Desktop, Cursor, etc.) and HTTP (production deployments)
Response Size Optimization -- 68-96% reduction in response sizes for LLM context efficiency
Type-Narrowed Schemas -- specific object/array types with per-parameter descriptions (no generic Value params)
Multi-Platform -- macOS, Linux, Windows (x64 and arm64)
Letta 0.16.x Compatible -- archives, conversations, MCP servers v2
MCP 2025-11-25 Compliant -- streamable HTTP transport with SSE
Compile-Time Routing -- zero runtime overhead for tool dispatch via TurboMCP v3 macros
## Quick Start
### npm (Recommended)
bash
npm install -g letta-mcp-server
The correct binary for your platform is installed automatically.
| Platform | Package |
| macOS Intel | letta-mcp-darwin-x64 |
| macOS Apple Silicon | letta-mcp-darwin-arm64 |
| Linux x64 | letta-mcp-linux-x64 |
| Linux arm64 | letta-mcp-linux-arm64 |
| Windows x64 | letta-mcp-windows-x64 |
### Docker
bash
docker pull ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
docker run -d \
-p 6507:6507 \
-e LETTABASEURL=http://your-letta-instance:8283 \
-e LETTAPASSWORD=your-password \
-e TRANSPORT=http \
--name letta-mcp \
ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
### Docker Compose
yaml
services:
letta-mcp:
image: ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
containername: letta-mcp
restart: unless-stopped
ports:
'6507:6507'
environment:
LETTABASEURL: ${LETTABASEURL}
LETTAPASSWORD: ${LETTAPASSWORD}
TRANSPORT: http
PORT: 6507
RUSTLOG: info
envfile:
.env
healthcheck:
test: ['CMD-SHELL', "timeout 1 bash -c '</dev/tcp/localhost/6507' || exit 1"]
interval: 30s
timeout: 10s
retries: 3
## Environment Variables
| Variable | Required | Default | Description |
| LETTABASEURL | Yes | — | Letta API URL (e.g. http://localhost:8283) |
| LETTAPASSWORD | Yes | — | Letta API password |
| TRANSPORT | No | stdio | Transport mode: stdio or http |
| PORT | No | 6507 | HTTP port (when TRANSPORT=http) |
| RUSTLOG | No | info | Log level: debug, info, warn, error |
| RUSTBACKTRACE | No | 0 | Enable backtraces (0 or 1) |
| LETTAMCPMAXVALUELEN | No | 500 | Max characters for block/passages/search values |
| LETTAMCPCOREMEMORYPREVIEWLEN | No | 200 | Max characters for core memory previews |
## Available Tools
The server provides 7 consolidated tools with 103 operations:
| Tool | Operations | Description |
| lettaagentadvanced | 28 | Agent lifecycle, messaging, conversations, context, export/import |
| lettamemoryunified | 24 | Core memory, blocks, archival passages, archives, search |
| lettatoolmanager | 13 | Tool CRUD, attach/detach, bulk operations |
| lettasourcemanager | 15 | Data sources, files, passages, attachments |
| lettajobmonitor | 4 | Job tracking, cancellation, active monitoring |
| lettafilefolderops | 8 | File sessions, folder management |
| lettamcpops | 11 | MCP server lifecycle, tool discovery, v2 API support |
## Features
7 Consolidated Tools covering 103 operations using the discriminator pattern
High Performance -- Rust, ~10-30MB memory, <500ms startup, parallel fan-out via tokio::join! and bufferunordered
Dual Transport -- stdio (Claude Desktop, Cursor, etc.) and HTTP (production deployments)
Response Size Optimization -- 68-96% reduction in response sizes for LLM context efficiency
Type-Narrowed Schemas -- specific object/array types with per-parameter descriptions (no generic Value params)
Multi-Platform -- macOS, Linux, Windows (x64 and arm64)
Letta 0.16.x Compatible -- archives, conversations, MCP servers v2
MCP 2025-11-25 Compliant -- streamable HTTP transport with SSE
Compile-Time Routing -- zero runtime overhead for tool dispatch via TurboMCP v3 macros
## Quick Start
### npm (Recommended)
bash
npm install -g letta-mcp-server
The correct binary for your platform is installed automatically.
| Platform | Package |
| macOS Intel | letta-mcp-darwin-x64 |
| macOS Apple Silicon | letta-mcp-darwin-arm64 |
| Linux x64 | letta-mcp-linux-x64 |
| Linux arm64 | letta-mcp-linux-arm64 |
| Windows x64 | letta-mcp-windows-x64 |
### Docker
bash
docker pull ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
docker run -d \
-p 6507:6507 \
-e LETTABASEURL=http://your-letta-instance:8283 \
-e LETTAPASSWORD=your-password \
-e TRANSPORT=http \
--name letta-mcp \
ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
### Docker Compose
yaml
services:
letta-mcp:
image: ghcr.io/oculairmedia/letta-mcp-server-rust:rust-latest
containername: letta-mcp
restart: unless-stopped
ports:
'6507:6507'
environment:
LETTABASEURL: ${LETTABASEURL}
LETTAPASSWORD: ${LETTAPASSWORD}
TRANSPORT: http
PORT: 6507
RUSTLOG: info
envfile:
.env
healthcheck:
test: ['CMD-SHELL', "timeout 1 bash -c '</dev/tcp/localhost/6507' || exit 1"]
interval: 30s
timeout: 10s
retries: 3
## Environment Variables
| Variable | Required | Default | Description |
| LETTABASEURL | Yes | — | Letta API URL (e.g. http://localhost:8283) |
| LETTAPASSWORD | Yes | — | Letta API password |
| TRANSPORT | No | stdio | Transport mode: stdio or http |
| PORT | No | 6507 | HTTP port (when TRANSPORT=http) |
| RUSTLOG | No | info | Log level: debug, info, warn, error |
| RUSTBACKTRACE | No | 0 | Enable backtraces (0 or 1) |
| LETTAMCPMAXVALUELEN | No | 500 | Max characters for block/passages/search values |
| LETTAMCPCOREMEMORYPREVIEWLEN | No | 200 | Max characters for core memory previews |
## Available Tools
The server provides 7 consolidated tools with 103 operations:
| Tool | Operations | Description |
| lettaagentadvanced | 28 | Agent lifecycle, messaging, conversations, context, export/import |
| lettamemoryunified | 24 | Core memory, blocks, archival passages, archives, search |
| lettatoolmanager | 13 | Tool CRUD, attach/detach, bulk operations |
| lettasourcemanager | 15 | Data sources, files, passages, attachments |
| lettajobmonitor | 4 | Job tracking, cancellation, active monitoring |
| lettafilefolderops | 8 | File sessions, folder management |
| lettamcpops | 11 | MCP server lifecycle, tool discovery, v2 API support |
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/oculairmedia-letta-mcp-server/)
- 来源
- awesome · https://github.com/oculairmedia/Letta-MCP-server
- 按领域浏览
- MCP 服务
- 收录来源
- 10 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。