Memanto MCP Server

@moorcheh-ai

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

moorcheh-ai

提交者

Hetkumar Patel

关于 Memanto MCP Server

MEMANTO is a memory agent. It remembers, recalls, and answers - so your agents can achieve long-term goals and avoid confusion.

#memory #ai-agents #long-term-memory #rag#semantic-memory#llm-memory #agent-memory#moorcheh#stateful-ai#memanto

Memanto MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "memanto": {
      "command": "memanto-mcp",
      "env": {
        "MOORCHEH_API_KEY": "<your-key>",
        "MEMANTO_DEFAULT_AGENT_ID": "my-project"
      }
    }
  }
}

Memanto MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Memanto MCP?

Memanto MCP is a server that exposes Memanto's persistent semantic memory primitives — remember, recall, answer, and related tools — as Model Context Protocol (MCP) tools. It allows any MCP-compatible client (Claude Desktop, Cursor, Windsurf, Cline, Continue, Goose, etc.) to store and retrieve typed semantic memories in a shared namespace using a Moorcheh API key. The server requires Python 3.10+ and a Moorcheh API key (free tier: 100K operations per month).

How to use Memanto MCP?

Install with pip install memanto-mcp. Set the MOORCHEH_API_KEY environment variable and optionally MEMANTO_DEFAULT_AGENT_ID. Add the server to your MCP client's configuration file (e.g., claude_desktop_config.json). The server registers seven memory tools by default; four agent‑management tools can be enabled via MEMANTO_EXPOSE_ADMIN=true. Transport can be stdio, sse, or streamable‑http, configured via environment variables or CLI flags (memanto-mcp --transport sse --port 8765).

Key features of Memanto MCP

Persistent semantic memory across MCP-compatible agents
Sub-90 ms retrieval with conflict detection
Shared memory namespace for multiple agents
Supports 13 memory types and 6 provenance values
RAG-based grounded answer tool using memories
Point-in-time and differential recall capabilities

Use cases of Memanto MCP

Remember user preferences and instructions across chat sessions
Recall decisions and context from previous conversations
Perform RAG over an agent’s stored knowledge for grounded answers
Track goals, commitments, and observations over time
Batch import extracted facts from documents using batch_remember

常见问题

What dependencies does Memanto MCP require?

Python 3.10+ and a Moorcheh API key. The free tier provides 100K operations per month.

How is the server authenticated?

The server authenticates to Moorcheh via the API key but does **not** authenticate inbound MCP clients; production deployments should pair it with a reverse proxy and authentication.

Which transports are supported?

The server supports `stdio` (default), `sse` (Server-Sent Events), and `streamable-http` (recommended modern transport). Transport is configured via the `MEMANTO_MCP_TRANSPORT` environment variable or CLI flags.

How does session management work?

On first memory tool call, a JWT session is activated and auto‑renews before expiry. Sessions are intentionally kept alive on shutdown so other Memanto clients can share them.

Can I embed Memanto MCP programmatically?

Yes. You can construct the FastMCP instance using `MCPServerSettings` and `build_server` from the `memanto_mcp` package, then add your own tools and run the server.

其他分类下的更多 MCP 服务器

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Volley.sh

Volley

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

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code