MCP Server: IPFS Context
[!WARNING]
Information is stored publically on IPFS network. Do not store sensitive information.
An MCP that uses IPFS to store and retrieve context between sessions.
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.
Tools
Usage:
Tools are automatcally called by the LLM prompts. You do not need to call them directly.
leave_off
Usage:
- Automatically called via MCP prompts with the required
contextparameter.
Stores the current conversation context and returns a unique identifier (id) for later retrieval.
pick_up
Retrieves previously stored context using the unique identifier obtained from leave_off.
Usage:
- Automatically called via MCP prompts with the required
idparameter.
Prompts
Customize your conversational workflows easily using prompts.
In Claude Desktop, activate by clicking "Attach to MCP", then select your desired prompt from the "Choose an integration" menu.
💾 Save
Summarizes the current conversation and utilizes the leave_off tool to store the context.
Optional Parameters:
projectType: Define the project type. Available options:general(default)technicalcreativeproblem-solving
includeMermaid: Include Mermaid diagrams (yesorno, default:no)includeCode: Include code snippets (yesorno, default:no)includeTasks: Include task lists (yesorno, default:no)
📂 Continue
Loads previously saved conversation context using the pick_up tool.
Required Parameter:
id: Unique identifier generated by theleave_offtool.
📂 Resume
Loads most recently saved convesation context.
Installation
Prerequisites
- Node.js
- MCP-compatible client (e.g., Claude Desktop)
Setup
Integrate into your MCP client configuration:
Using NPX:
{
"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>"
]
}
}
}
License
MIT
Recommend MCP Servers 💡
godot-rag
An MCP server designed to provide Godot documentation as context for a Godot RAG model.
@1mcp/agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
package-registry-mcp
A Model Context Protocol (MCP) server that enables AI assistants and agents to search and retrieve up-to-date information from NPM, Cargo, PyPI, NuGet, and Go package registries.
@modelcontextprotocol/server-github
An MCP server for the GitHub API, providing functionalities for file operations, repository management, and search.
kcve
An MCP server that reads information on Linux Kernel CVEs by querying an SQLite database populated from the Linux kernel CVE list.
exa-mcp-server
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches.