MEFS MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MEFS MCP Server upload my report to MEFS"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MEFS-MCP-SERVER
MEMO MCP Server provides a standard storage interface for AI agents, allowing AI agents to save generated content to MEFS and providing data retrieval capabilities. It provides decentralized storage for AI agents.
Use Cases
Encrypted data storage: Store AI-generated content to MEFS.
User context retrieval: Store user behavior and preference data to MEFS, and quickly retrieve relevant user data in subsequent requests to provide to AI agents.
Seamless data sharing: AI agents can achieve trustless data sharing through content identifiers (CID).
Related MCP server: MemoraМCP
Free Quota
Start using mefs-storage now and enjoy 10GB of free storage space.
Quick Installation Guide
You can follow the steps below to install the MCP server. Before using the MEFS MCP server, please ensure you have created an EVM private key.
Prerequisites
Before using the MEFS MCP server, please ensure you have created an EVM private key. You can use EVM wallets such as MetaMask or Okx Wallet to create a wallet and obtain your private key.
Configure MCP Server (Private Key Required)
You can start the MCP server in your client using the following configuration:
Standard Configuration - Suitable for most clients
{
"mcpServers": {
"mefs-storage-server": {
"command": "npx",
"args": ["mefs-mcp-server"],
"env": {
"MCP_TRANSPORT_MODE": "stdio",
"MEFS_PRIVATE_KEY": "<YOUR-PRIVATE-KEY>",
},
"shell": true,
"cwd": "./",
},
},
}Replace YOUR-PRIVATE-KEY with your EVM private key obtained from the EVM wallet.
SSE Mode
The MEFS MCP Storage Server supports SSE transport mode. you can start sse mode with following step:
Clone Repository
git clone https://github.com/memoio/mefs-mcp-server.git && cd mefs-mcp-serverInstall Dependencies
pnpm installBuild
pnpm run buildStart with SSE mode
pnpm run start:sseYou can configure MEFS_PRIVATE_KEY in your .env file, add MEFS_PRIVATE_KEY to your path with export command, or start the system using the following command to use your EVM private key:
MEFS_PRIVATE_KEY=<YOUR-PRIVATE-KEY> pnpm run start:sseConfigure MCP Server (SSE mode)
{
"mcpServers": {
"mefs-storage-server": {
"url": "http://localhost:3001/sse",
},
},
}Using MCP Tools
MEFS MCP Server provides the following tools to interact with the decentralized storage network MEFS:
Upload
Upload files to MEFS:
// Example usage in an AI application
const result = await uploadFile({
file: base64EncodedContent,
name: "document.pdf",
});Parameters:
file: Base64-encoded file contentname: Filename with extension
Retrieve
Retrieve files from the MEFS network:
// Example retrieval by CID
const document = await retrieveFile({ cid: "bafybei...gq5a/document.pdf"});Parameters:
cid: Unique identifier of the file
Check Remaining Space
Check remaining storage space:
const identity = await getSpace({});Available Tools
2 toolsretrieveA
Retrieve a file from MEFS storage by its CID (Content ID). Returns the file content as a base64 encoded string.
Inputs: cid (required), key.
uploadA
Upload a file to MEFS storage. The file must be provided as a base64 encoded string. Returns the CID (Mid) of the uploaded file.
Inputs: file (required), name (required), key, public.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves a file by CID, the other uploads a file. There is no overlap or ambiguity.
Both tool names are single lowercase verbs ('retrieve', 'upload') following a consistent pattern.
With only two tools, the server feels thin for a storage system, but it covers the core upload and retrieve operations. It is borderline but reasonable for a very focused use case.
Obvious gaps exist: there is no tool for listing stored files, deleting files, or updating existing content. These missing operations will cause agent failures if management beyond upload/retrieve is needed.
Maintenance
Related MCP Connectors
Persistent file storage for AI agents. Save files over MCP, get a link a human can open.
Searchable storage for AI agents: store, find, read and trust artifacts shared between agents.
Encrypted A2A object storage for autonomous agent state and artifacts
Private, permanent encrypted storage for AI agents. Paid per call in USDC via x402.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI applications to interact with decentralized storage through a standardized Model Context Protocol interface, allowing file uploads, retrievals, and identity management.13Apache 2.0
- FlicenseNot gradedqualityDmaintenanceAn MCP-powered storage system for AI agents that provides IPFS-secured, verifiable, and sovereign data storage capabilities.-
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with seamless access to Filecoin's decentralized storage network for persistent file storage and dataset management. It features automatic payment handling, CDN support, and cost estimation tools for efficient storage operations.26 npm12MIT
- AlicenseNot gradedqualityDmaintenanceProvides encrypted, portable memory for AI agents via MCP, allowing fact storage, conversation recall, and cross-machine sync using Arweave.50MIT