Skip to main content
Glama

MARU Japan Hands

Connect to a MARU wallet

maru_wallet_connect

Connect this AI to the user's MARU wallet (Japanese yen stablecoin, JPYC). The user creates a one-time pairing code in the MARU app (Security > Let AI pay > Add an AI) and tells it to you. Returns an agent token and a 4-symbol fingerprint: tell the user the fingerprint and ask them to approve this AI in the MARU app with Face ID. Until they approve, the token does nothing. Keep the token for later calls; never show it to anyone else.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pairing_code": "<pairing_code>",
      "agent_name": "<agent_name>"
    },
    "name": "maru_wallet_connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_nameYesA short name the user will recognise in their app, e.g. 'Claude (work laptop)'.
pairing_codeYesCode shown in the MARU app, like ABCD-2345. Valid for 10 minutes, usable once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare the non-read-only, non-idempotent, non-destructive, non-open-world profile; the description adds the real behavior: a token and 4-symbol fingerprint are returned, the token is inert until the user approves with Face ID, and the token must be kept but never disclosed. That is exactly the post-call workflow an agent cannot infer from the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences ordered by workflow: what it connects, how to obtain the code, what comes back and what the user must do next. No filler, and the critical follow-up action is front-loaded before the token-handling constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return value itself (agent token plus fingerprint) and the pending-approval state, plus secret-handling rules. For a two-parameter auth tool this covers everything needed to call it and act on the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, and the description mostly restates them (one-time code from the app, names shown to the user). The only genuine addition is the in-app navigation path for obtaining the pairing code, which is a small increment over the schema's own wording.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Connect this AI to the user's MARU wallet') plus the currency context (JPYC), so the onboarding role is unmistakable against payment-request siblings. An agent can tell this is the setup step rather than a transaction step without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames the precondition: the user must create a one-time pairing code in the MARU app (Security > Let AI pay > Add an AI) and hand it over, which tells the agent when the call is possible. It stops short of naming sibling alternatives (e.g. that this must precede maru_wallet_request_payment), so 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.