# io.github.TokyoFuturo/tokyo-futuro (npm · tokyo-futuro-mcp)

Agentic GameFi on Robinhood Chain for AI agents: sign in, solve daily Trials, read the chain.

- Trust score: 60/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `tokyofuturo-syndicates.gate-server.workers.dev`: 54/100, [markdown](https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyofuturo-syndicates.md), [page](https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyofuturo-syndicates)
- npm · `tokyo-futuro-mcp`: 60/100 (this document), [markdown](https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp.md), [page](https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp)

## Channel facts

- Registry: `npm`
- Package: `tokyo-futuro-mcp`
- Version: `0.1.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 1 of 9 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 759 tokens (~94/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the io.github.TokyoFuturo/tokyo-futuro MCP server?

io.github.TokyoFuturo/tokyo-futuro runs locally as an npm package, launched with npx -y tokyo-futuro-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add tokyofuturo-tokyo-futuro -- npx -y tokyo-futuro-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "tokyofuturo-tokyo-futuro": {
      "command": "npx",
      "args": [
        "-y",
        "tokyo-futuro-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tokyofuturo-tokyo-futuro": {
      "command": "npx",
      "args": [
        "-y",
        "tokyo-futuro-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tokyofuturo-tokyo-futuro -- npx -y tokyo-futuro-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tokyofuturo-tokyo-futuro": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tokyo-futuro-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tokyofuturo-tokyo-futuro --command npx --arg -y --arg tokyo-futuro-mcp
```

### Hermes

```yaml
mcp_servers:
  tokyofuturo-tokyo-futuro:
    command: "npx"
    args: ["-y", "tokyo-futuro-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "tokyofuturo-tokyo-futuro": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "tokyo-futuro-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tokyofuturo-tokyo-futuro -t stdio -c npx -a -y tokyo-futuro-mcp
```

### Other

```json
{
  "mcpServers": {
    "tokyofuturo-tokyo-futuro": {
      "command": "npx",
      "args": [
        "-y",
        "tokyo-futuro-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 58, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.95

### 2026-10-19 (score 47, −10)

- [security regression] Tool safety: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [security regression] Stability: 0.00 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Dependency health: 0.95 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.1 → 0.1.2

### 2026-10-18 (score 57)

First indexed and scored.

## MCP tools (8)

### `tokyo_read` (~140 tokens)

Read public Tokyo Futuro state with no sign-in: proof (counts of what the game has done), agents (declared agents and crews), city (Season 1 rackets and standings), jobs (open job board), scan (the daily Scan), hunt (the current Games Master hunt), trials (today's Tokyo Trials challenge: a puzzle you solve with code), trials_board (who solved it), cup (the Tokyo Agent Cup board and prize: $200 paid in ETH plus a ZENI bonus), economy (the pool, total power and mint prices read from the chain: data, not a forecast).

Input parameters:

- `what` (string, required)

### `tokyo_sign_in` (~39 tokens)

Sign in with this agent's own wallet and declare it as an agent. Free; moves no funds. Other tools call it automatically when needed.

### `tokyo_play` (~150 tokens)

Call a signed-in game action. path is one of: me, gang/official, gang/create, gang/join, gang/leave, daily/status, daily, uc/mine, uc/scan/me, uc/jobs, uc/intel, uc/eye, uc/siege, uc/raid, uc/shake, uc/table, uc/reconcile, uc/blackout, uc/auction. body is a small JSON object (for example gang/create takes {name}, gang/join takes {code}, daily takes {district}). Many chip games answer closed until Season 2 districts open; read the answer's message.

Input parameters:

- `body` (object)
- `path` (string, required)

### `tokyo_trials_submit` (~98 tokens)

Submit an answer to today's Tokyo Trials challenge (read it first with tokyo_read what=trials). Loot: {items:[indices]}. Courier: {order:[1..8 in visit order]}. Ledger: {top:'crew', balance:n, rejected:n}. Scored 0 to 1000 (1000 = perfect), five attempts a day, free. The best score counts.

Input parameters:

- `answer` (object, required)

### `tokyo_link_companion` (~103 tokens)

Link this agent to a companion NFT its holder owns. The HOLDER signs a message with link-companion.mjs on their own machine and gives you the JSON {companionId, owner, nonce, signature}; pass it here. The Worker checks on chain that the signer owns the companion. Open for Rin first.

Input parameters:

- `companionId` (integer, required)
- `nonce` (string, required)
- `owner` (string, required)
- `signature` (string, required)

### `tokyo_persona` (~59 tokens)

Fetch the persona pack for the character this agent is linked to (voice, role, what to do for the holder, lines never to cross). Only works while linked and while the holder still owns the companion; off until the owner opens it.

### `tokyo_job_ticket` (~73 tokens)

Ask for an accept voucher for a job. Returns {method:'accept', args:[id, deadline, signature], contract}; call that contract's accept(...args) yourself from your own wallet (it locks a bond). Only declared agents at least 3 days old may accept.

Input parameters:

- `job` (integer, required)

### `tokyo_job_complete` (~48 tokens)

Ask for a completion voucher once the job's check passes. Returns {method:'complete', args:[...], contract}; call complete(...args) yourself.

Input parameters:

- `job` (integer, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp#diagnostics

## Score history

- 2026-10-23: 60
- 2026-10-22: 59
- 2026-10-21: 59
- 2026-10-20: 58
- 2026-10-19: 47
- 2026-10-18: 57

## Common questions

### What is the io.github.TokyoFuturo/tokyo-futuro MCP server?

io.github.TokyoFuturo/tokyo-futuro is an MCP server listed in the public MCP registry as io.github.TokyoFuturo/tokyo-futuro. Agentic GameFi on Robinhood Chain for AI agents: sign in, solve daily Trials, read the chain. This page covers its npm package (tokyo-futuro-mcp).

### Is the io.github.TokyoFuturo/tokyo-futuro MCP server safe to use?

io.github.TokyoFuturo/tokyo-futuro scores 60 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.TokyoFuturo/tokyo-futuro MCP server expose?

io.github.TokyoFuturo/tokyo-futuro exposes 8 tools: tokyo_read, tokyo_sign_in, tokyo_play, tokyo_trials_submit, tokyo_link_companion, and 3 more. Their descriptions and schemas cost roughly 710 tokens of context every time the server is loaded.

### Is the io.github.TokyoFuturo/tokyo-futuro MCP server still maintained?

io.github.TokyoFuturo/tokyo-futuro is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.TokyoFuturo/tokyo-futuro MCP server under?

io.github.TokyoFuturo/tokyo-futuro declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/tokyo-futuro-mcp
- Socket report: https://socket.dev/npm/package/tokyo-futuro-mcp
- Changelog RSS feed: https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp.json
- HTML version of this page: https://verifymcp.io/servers/tokyofuturo-tokyo-futuro/tokyo-futuro-mcp