mcpField
M
MyMultiSig

MyMultiSig

Local
mymultisig.appFinance0Updated today
RepositoryVisit website

About MyMultiSig

MyMultiSig is an MCP server for managing MyMultiSig multisignature wallets through AI clients. It supports wallet inspection and transaction review as well as proposing, signing, and executing transactions, with configurable chain access and read-only mode.

Key features

  1. 01Inspect wallets and requests
  2. 02Decode calls and show risk warnings
  3. 03Propose, approve, and execute transactions
  4. 04Create and manage multisig wallets
  5. 05Restrict chains or enable read-only mode

Use cases

  1. 01Review a multisig request before signing
  2. 02Propose transactions from an AI client
  3. 03Execute approved requests with simulation
  4. 04Limit an agent to read-only wallet access

MCP support

The MCP server exposes read and write tools for MyMultiSig wallets to clients such as Claude and Cursor. Write tools include safety annotations, and server instructions require review and approval before signing or execution.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "marc-aurele-besner-mymultisig": {
      "command": "npx",
      "args": [
        "-y",
        "mymultisig-mcp"
      ],
      "env": {
        "MYMULTISIG_API_KEY": "<MYMULTISIG_API_KEY>",
        "MYMULTISIG_PRIVATE_KEY": "<MYMULTISIG_PRIVATE_KEY>",
        "MYMULTISIG_CHAINS": "<MYMULTISIG_CHAINS>",
        "MYMULTISIG_READ_ONLY": "<MYMULTISIG_READ_ONLY>",
        "MYMULTISIG_ALLOW_SOLO_EXECUTION": "<MYMULTISIG_ALLOW_SOLO_EXECUTION>",
        "MYMULTISIG_API_URL": "<MYMULTISIG_API_URL>"
      }
    }
  }
}
Run commandnpx -y mymultisig-mcp
Environment variables to set
MYMULTISIG_API_KEYSecretScoped API key (mms_…) from https://mymultisig.app/settings/agents; acts as your wallet on the API
MYMULTISIG_PRIVATE_KEYSecretThe agent's own owner key (0x + 64 hex). Enables signing, executing and deploying; used locally only
MYMULTISIG_CHAINSComma-separated chain id allowlist, e.g. 11155111
MYMULTISIG_READ_ONLYSet to 1 to register read-only tools
MYMULTISIG_ALLOW_SOLO_EXECUTIONSet to 1 to let the agent execute without another owner's approval (off by default)
MYMULTISIG_API_URLAPI base URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmymultisig-mcp0.1.3

Tools

15

Saved tool list · updated 2d ago

This tool takes no parameters.

Details

From the project README

mymultisig-mcp

This is a Model Context Protocol server for MyMultiSig multi-signature wallets. It lets Claude, Cursor or any MCP client inspect wallets, decode and review requests, propose transactions, sign them and execute them.

Setup

Claude Code

claude mcp add mymultisig \
  -e MYMULTISIG_API_KEY=mms_… \
  -e MYMULTISIG_PRIVATE_KEY=0x… \
  -e MYMULTISIG_CHAINS=11155111 \
  -- npx -y mymultisig-mcp

You can also install the plugin, which adds workflow skills on top of the server:

/plugin marketplace add marc-aurele-besner/mymultisig-app
/plugin install mymultisig@mymultisig

Other clients (Claude Desktop, Cursor, …)

{
  "mcpServers": {
    "mymultisig": {
      "command": "npx",
      "args": ["-y", "mymultisig-mcp"],
      "env": { "MYMULTISIG_API_KEY": "mms_…", "MYMULTISIG_PRIVATE_KEY": "0x…" }
    }
  }
}
Env varMeaning
MYMULTISIG_API_KEYScoped key from https://mymultisig.app/settings/agents. It acts as your wallet on the API.
MYMULTISIG_PRIVATE_KEYThe agent's own owner key. The agent needs it to sign approvals, execute and deploy. It is used locally and never sent anywhere.
MYMULTISIG_CHAINSAllowlist of chain ids, comma-separated.
MYMULTISIG_READ_ONLYSet to 1 to register read tools only.
MYMULTISIG_RPC_URL_<chainId>Custom RPC for a chain.
MYMULTISIG_API_URLDefaults to https://mymultisig.app.

Tools

  • Read:
    • whoami, list_networks;
    • get_multisig, list_my_multisigs, list_requests;
    • get_request: the decoded call, risk warnings and locally verified signatures;
    • get_balances, predict_multisig_address, encode_function_call.
  • Write:
    • create_multisig, propose_transaction;
    • approve_request;
    • execute_request: simulates first and refuses when signatures are missing or invalid;
    • cancel_request, reset_request.

Write tools carry MCP annotations (destructiveHint and similar), so clients can ask you for confirmation. The server's instructions also tell the model to show get_request output and get your approval before it signs or executes.

Safety: give the agent a threshold it can't reach on its own, keep API key scopes to the minimum, and start on a testnet. See https://mymultisig.app/docs/ai-agents.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.