Model Context Protocol (MCP) server for freee API integration
Nothing to run from here
MyMultiSig is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
426
downloads a day
local
runs on your machine
857
downloads in 30d
What it does
Create, review, sign and execute MyMultiSig multisig wallet transactions from AI agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mymultisig-mcp '--' npx -y mymultisig-mcp
# 2 — ask your agent for something these tools do
# whoami, list_networks, get_multisig and 12 more
MyMultiSig costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MAAll 1 server
marc-aurele-besner1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts MyMultiSig as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user mymultisig-mcp '--' npx -y mymultisig-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take MYMULTISIG_API_KEY (Scoped API key (mms_…) from https://mymultisig.app/settings/agents; acts as your wallet on the API), MYMULTISIG_PRIVATE_KEY (The agent's own owner key (0x + 64 hex). Enables signing, executing and deploying; used locally only), MYMULTISIG_CHAINS (Comma-separated chain id allowlist, e.g. 11155111), MYMULTISIG_READ_ONLY (Set to 1 to register read-only tools), MYMULTISIG_ALLOW_SOLO_EXECUTION (Set to 1 to let the agent execute without another owner's approval (off by default)), MYMULTISIG_API_URL (API base URL) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Which credentials this server runs with: the local signing address (if MYMULTISIG_PRIVATE_KEY is set), the API key owner and scopes (if MYMULTISIG_API_KEY is set), and whether write tools are enabled.
No parameter schema on file.
Chains MyMultiSig supports, with the official factory address and version on each.
No parameter schema on file.
Live on-chain state of a MyMultiSig wallet: name, contract version, owners, threshold, nonce, wallet type.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| address | string | yes | — |
Wallets registered on mymultisig.app for an owner (defaults to the API key owner or the agent signer). Needs an API key with the read scope, or a signing key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| owner | string | no | — |
Active transaction requests queued for a wallet, in execution order, with signature counts vs threshold and a one-line summary of each.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| wallet | string | yes | — |
Full detail of one request: decoded call with risk warnings, every signature verified locally against the owner set, whether the agent already signed, and whether it is ready to execute. Call this before approving or executing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| requestId | string | yes | — |
Native balance plus ERC-20 tokens and NFTs held by an address (token data via the app indexer).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| address | string | yes | — |
CREATE2 address a 0.5.0 factory will deploy to for this creator, salt and constructor arguments (same on every chain with the same factory).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| name | string | yes | — |
| owners | array | yes | — |
| threshold | integer | yes | — |
| salt | string | yes | bytes32 salt, 0x + 64 hex chars |
| walletType | string | no | simple = MyMultiSig; extended/advanced = MyMultiSigExtended (owner-only requests, ERC-4337, …) |
| onlyOwnerRequest | boolean | no | — |
| creator | string | no | defaults to the agent signer |
| factory | string | no | — |
ABI-encode a contract call into hex calldata for propose_transaction, and echo back its decoded summary.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| abi | yes | JSON ABI array as a string, or human-readable signature(s) like "function transfer(address,uint256)" | |
| functionName | string | yes | — |
| args | array | no | Arguments in order; pass uint values as decimal strings |
| to | string | no | Target contract, only used for the summary |
| wallet | string | no | The multisig, only used to recognise self-calls in the summary |
Deploy a MyMultiSig wallet from the official factory (the agent key pays gas) and register it on mymultisig.app. Needs MYMULTISIG_PRIVATE_KEY. Refuses a wallet the agent could operate alone (agent is an owner and threshold is 1). Confirm owners, threshold and chain with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| name | string | yes | — |
| owners | array | yes | — |
| threshold | integer | yes | — |
| walletType | string | no | simple = MyMultiSig; extended/advanced = MyMultiSigExtended (owner-only requests, ERC-4337, …) |
| onlyOwnerRequest | boolean | no | Extended/advanced only: only owners may queue requests |
| salt | string | no | bytes32 salt for a deterministic (CREATE2) address on 0.5.0 factories |
| factory | string | no | Defaults to the official factory on the chain |
Queue a transaction request on a multisig. Provide either raw data, or abi + functionName + args to encode it. With MYMULTISIG_PRIVATE_KEY (an owner) the agent signs it immediately; otherwise it is queued unsigned for the owners to sign in the app. Returns the request link to share.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| wallet | string | yes | The multisig wallet address |
| to | string | yes | Destination of the call |
| value | string | no | Native value in wei (default 0) |
| valueEther | string | no | Native value as a decimal in ether units, alternative to value |
| data | string | no | Raw calldata (default 0x) |
| abi | no | JSON ABI array as a string, or human-readable signature(s) like "function transfer(address,uint256)" | |
| functionName | string | no | — |
| args | array | no | — |
| description | string | yes | Human-readable purpose, shown to the other owners |
| txnGas | string | no | Gas forwarded to the inner call; estimated when omitted |
| txnNonce | string | no | Extended wallets: pin to an explicit nonce |
| validUntil | string | no | 0.5.0 wallets: unix-seconds expiry of the signatures |
| delegatecall | boolean | no | 0.5.0 Extended only, DANGEROUS: execute via DELEGATECALL |
| sign | boolean | no | Set false to queue without the agent signature |
Add the agent’s EIP-712 signature to a queued request. Needs MYMULTISIG_PRIVATE_KEY for an owner. Refuses if any existing signature is invalid. Only call after showing get_request output to the user and getting confirmation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| requestId | string | yes | — |
Send execTransaction for a request that has reached its threshold (the agent key pays gas). Simulates first and refuses on missing/invalid signatures, or when no owner other than the agent has approved. Irreversible: confirm with the user first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chainId | integer | yes | EVM chain id, e.g. 11155111 for Sepolia (see list_networks) |
| requestId | string | yes | — |
Cancel a queued request (owner-only). Later requests in the queue are invalidated server-side (their signatures are wiped).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| requestId | string | yes | — |
Wipe all signatures on a request (owner-only), e.g. after the wallet nonce moved. Later requests in the queue are invalidated too.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| requestId | string | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install MyMultiSig or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.1.3 · scanned 10 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest16b454ccd6f008a3f719e115542f514c969c57c857fe708e22727aec4839c96a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
6 of the 15 recovered tools are registered only when options.readOnly is false (dist/index.js:256) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
9 tools are registered unconditionally · 6 more only when options.readOnly is false (dist/index.js:256) — typically when a key or option is configured. All 15 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| whoami | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_networks | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_multisig | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_my_multisigs | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_requests | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_request | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_balances | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| predict_multisig_address | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| encode_function_call | no tags | |
| create_multisig conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| propose_transaction conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| approve_request conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| execute_request conditional | external-sink | external-sink: declares destructiveHint: true, openWorldHint: true |
| cancel_request conditional | external-sink | external-sink: declares destructiveHint: true, openWorldHint: true |
| reset_request conditional | external-sink | external-sink: declares destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest16b454ccd6f008a3
Scanned2026-11-10
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.3. Pin a release below and the command asks for exactly that one.
0.1.3
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish MyMultiSig can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.