mcp-server-ipfs-context

johnhenry/mcp-server-ipfs-context

3.2

If you are the rightful owner of mcp-server-ipfs-context and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

This document provides a structured overview of an MCP server that utilizes IPFS for storing and retrieving conversational context.

The MCP Server: IPFS Context is a model context protocol server designed to facilitate the storage and retrieval of conversational context using the InterPlanetary File System (IPFS). This server is particularly useful for applications that require persistent context across sessions, such as chatbots or virtual assistants. By leveraging IPFS, the server ensures that information is stored in a decentralized manner, enhancing accessibility and reliability. The server supports various features that make it easy to integrate into existing workflows, including customizable prompts and support for structured content like diagrams and code snippets. It is compatible with MCP clients such as Claude Desktop, allowing users to seamlessly save and resume conversations.

Features

  • Easy-to-use tools for persisting and retrieving conversational context.
  • Customizable prompts for efficient workflow integration.
  • Support for structured content including Mermaid diagrams, code snippets, and tasks.

Usages

npx with Claude Desktop

{
  "mcpServers": {
    "vimble-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-server-ipfs-context", "<path-to-context-storage>"]
    }
  }
}

local development

{
  "mcpServers": {
    "vimble-mcp": {
      "command": "<path-to-node>",
      "args": [
        "<this-directory>/stdio.mjs",
        "<ipfs-gateway-url>",
        "<ipfs-gateway-url>"
      ]
    }
  }
}

Tools

  1. leave_off

    Stores the current conversation context and returns a unique identifier for later retrieval.

  2. pick_up

    Retrieves previously stored context using the unique identifier obtained from leave_off.