# dev.clusteragent/cluster-mcp (npm · @clusteragent/cluster-mcp)

Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- remote · `mcp.clusteragent.dev`: 28/100, [markdown](https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/mcp.md), [page](https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/mcp)
- npm · `@clusteragent/cluster-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/clusteragent-cluster-mcp.md), [page](https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/clusteragent-cluster-mcp)

## Channel facts

- Registry: `npm`
- Package: `@clusteragent/cluster-mcp`
- Version: `1.0.12`
- 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 2026-09-25.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1772 tokens (~49/item across 36 items; 36 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 23% 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 36 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the dev.clusteragent/cluster-mcp server?

dev.clusteragent/cluster-mcp runs locally as an npm package, launched with npx -y @clusteragent/cluster-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 dev-clusteragent-cluster-mcp -- npx -y @clusteragent/cluster-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "dev-clusteragent-cluster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clusteragent/cluster-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-clusteragent-cluster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clusteragent/cluster-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dev-clusteragent-cluster-mcp -- npx -y @clusteragent/cluster-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-clusteragent-cluster-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@clusteragent/cluster-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-clusteragent-cluster-mcp --command npx --arg -y --arg @clusteragent/cluster-mcp
```

### Hermes

```yaml
mcp_servers:
  dev-clusteragent-cluster-mcp:
    command: "npx"
    args: ["-y", "@clusteragent/cluster-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "dev-clusteragent-cluster-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@clusteragent/cluster-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-clusteragent-cluster-mcp -t stdio -c npx -a -y @clusteragent/cluster-mcp
```

### Other

```json
{
  "mcpServers": {
    "dev-clusteragent-cluster-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clusteragent/cluster-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.

### 2026-09-25 (score 67, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-22 (score 67, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-21 (score 52)

First indexed and scored.

## MCP tools (36)

### `get_quotes` (~82 tokens)

Batch quotes + ~1 month of daily closes for tokenized stocks/ETFs and crypto on Robinhood Chain. Symbols: NVDA, SPY, TSLA, PONS, WETH, USDG, CLIPPY, KARMA, ...

Input parameters:

- `symbols` (string, required): Comma-separated symbols, e.g. 'NVDA,SPY,PONS'

### `get_movers` (~39 tokens)

Live gainers, losers and sector heat across the 192-instrument universe.

Input parameters:

- `limit` (number): Rows per side (default 10)

### `get_news` (~20 tokens)

Yahoo Finance market headlines.

Input parameters:

- `limit` (number)

### `get_chart` (~59 tokens)

Price series + candles for a symbol (NVDA, SPY, PONS, ...).

Input parameters:

- `symbol` (string, required)
- `tf` (string): 1d|5d|1mo|3mo|6mo|1y

### `get_index` (~26 tokens)

Cluster index composition: 193 instruments, on-chain verified count, $CLST status.

### `get_payout_basket` (~29 tokens)

The 19-name payout basket with weights — what $CLST holders get paid from.

### `get_distributions` (~33 tokens)

Distribution cycles, per-cycle aggregates, basket buys and treasury balance — the public payout record. Recipient lists are never public.

### `quote_swap` (~104 tokens)

Uniswap v3 route + amountOut for a swap on Robinhood Chain (4663). amount is in WEI of the input token. Read-only — execution happens in the user's wallet.

Input parameters:

- `amount` (string, required): Amount in wei of input token
- `side` (string, required): buy (ETH->token) or sell (token->ETH)
- `token` (string, required): Output token contract address
- `via` (string): USDG or WETH hop preference

### `trade_status` (~30 tokens)

Router, quoter, WETH, USDG, gas price, ETH USD rate for Robinhood Chain.

### `wallet_balances` (~40 tokens)

On-chain balances for any address on Robinhood Chain: native ETH + every held token. Read-only, no auth.

Input parameters:

- `address` (string, required)

### `get_models` (~27 tokens)

24-model LLM gateway list with context windows and USD pricing per 1M tokens.

### `chat` (~97 tokens)

One completion through the cluster LLM gateway (24 models). Set thinking=true for extended reasoning. Costs credit ($5 free per wallet).

Input parameters:

- `messages` (array, required)
- `model` (string): e.g. openai/gpt-6-astra, anthropic/..., glm/glm-5.3-flash (cheapest)
- `thinking` (boolean): Extended reasoning pass (uses more tokens)
- `wallet` (string)

### `get_credits` (~32 tokens)

Inference credit balance (granted/used/remaining) for a wallet.

Input parameters:

- `wallet` (string, required)

### `memory_retain` (~107 tokens)

Store a durable memory note. Works without a wallet (an anonymous agent bank is auto-created locally); pass a wallet/bank_id to use a private signature-gated wallet bank. Deduped — identical content is skipped. Persists across sessions.

Input parameters:

- `bank_id` (string): Optional. Wallet address or bank id; omit for the anonymous agent bank
- `content` (string, required): Max 4000 chars
- `tags` (array)
- `title` (string)

### `memory_recall` (~75 tokens)

Recall memory notes, scored by semantic relevance with recency decay. Works without a wallet (anonymous agent bank); pass bank_id for a wallet bank.

Input parameters:

- `bank_id` (string): Optional. Wallet address or bank id; omit for the anonymous agent bank
- `limit` (number)
- `query` (string, required)

### `create_key` (~56 tokens)

Create a cluster API key (clst_...) for a wallet. Shown exactly once.

Input parameters:

- `name` (string)
- `session_token` (string)
- `signature` (string)
- `wallet` (string, required)

### `key_usage` (~45 tokens)

Metered usage for a wallet's keys: requests, tokens, USD.

Input parameters:

- `session_token` (string)
- `signature` (string)
- `wallet` (string, required)

### `token_safety` (~55 tokens)

Safety scan for a Robinhood Chain token: liquidity depth, buy/sell ratio honeypot heuristic, holder count via explorer, launchpad-factory detection. Returns score, tier, flags.

Input parameters:

- `address` (string, required)

### `compare_tokens` (~53 tokens)

Side-by-side token comparison: price, 24h change, liquidity, volume for 2+ tokens (stocks or crypto).

Input parameters:

- `symbols` (string, required): Comma-separated, e.g. 'NVDA,PONS'

### `sector_heat` (~26 tokens)

Sector heat: average day change, advancers/decliners per sector across the universe.

### `agent_list` (~32 tokens)

The 16 cluster agent capabilities: Relay, Scout, Argus, Vault, Oracle, ... with categories and triggers.

### `agent_run` (~83 tokens)

Queue a public agent capability run; returns run id/status, then poll get_run_status for cited result. No treasury or signing side effect.

Input parameters:

- `agent_id` (string, required)
- `idempotency_key` (string)
- `label` (string)
- `session_token` (string)
- `signature` (string)
- `wallet` (string)

### `get_run_status` (~55 tokens)

Read a queued agent run's status, cited result, and retryable failure state.

Input parameters:

- `id` (number, required)
- `session_token` (string)
- `signature` (string)
- `wallet` (string, required)

### `get_position` (~34 tokens)

Wallet's index position: $CLST balance read on-chain (honest zeros pre-launch).

Input parameters:

- `wallet` (string, required)

### `get_portfolio` (~43 tokens)

Portfolio view + history for a wallet (wallet-auth required).

Input parameters:

- `session_token` (string)
- `signature` (string)
- `wallet` (string, required)

### `list_conversations` (~46 tokens)

Chat conversation list for a wallet (wallet-auth required — titles are private).

Input parameters:

- `session_token` (string)
- `signature` (string)
- `wallet` (string, required)

### `agent_quotes` (~27 tokens)

Real quotes for every agent that has a market analogue (mapped symbols). No-auth market data.

### `token_info` (~33 tokens)

Token metadata on-chain: symbol, decimals, total supply for any 4663 address.

Input parameters:

- `address` (string, required)

### `social_profile` (~25 tokens)

X (Twitter) link status for a wallet.

Input parameters:

- `wallet` (string, required)

### `memory_consolidate` (~56 tokens)

Two-pass memory consolidation: recall fragments, LLM synthesizes, retain the summary. Reduces note bloat.

Input parameters:

- `bank_id` (string, required)
- `session_token` (string)
- `signature` (string)

### `dca_preview` (~88 tokens)

DCA plan calculator (dry-run, no txs): quote N buys of X ETH each into a token, returns per-buy expected amounts + total at current prices. Real execution = sign each buy with your wallet (see skills/swap).

Input parameters:

- `buys` (number, required)
- `eth_per_buy` (string, required): e.g. '0.01'
- `token` (string, required)

### `tpsl_preview` (~86 tokens)

Bracket preview for a held token: current price from DexScreener, suggested TP/SL offsets (±10/20%), and the sell-side quote at those levels. Dry-run — no orders stored.

Input parameters:

- `amount_tokens` (string, required): wei
- `sl_pct` (number)
- `token` (string, required)
- `tp_pct` (number)

### `wallet_value` (~32 tokens)

USD valuation of a wallet: on-chain balances × live quotes, with concentration breakdown.

Input parameters:

- `address` (string, required)

### `basket_vs_wallet` (~40 tokens)

Compare a wallet's holdings against the 19-name payout basket: which basket names are missing, overweight, underweight.

Input parameters:

- `address` (string, required)

### `news_for_symbol` (~34 tokens)

Headlines filtered for relevance to one symbol's sector/company.

Input parameters:

- `limit` (number)
- `symbol` (string, required)

### `gas_now` (~23 tokens)

Current gas price + ETH USD on 4663 (from trade status).

## Diagnostics

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

## Score history

- 2026-09-25: 67
- 2026-09-24: 67
- 2026-09-23: 67
- 2026-09-22: 67
- 2026-09-21: 52

## Common questions

### What is the dev.clusteragent/cluster-mcp server?

dev.clusteragent/cluster-mcp is listed in the public MCP registry as dev.clusteragent/cluster-mcp. Self-hostable index of AI financial agents, tokenized stocks + crypto, memory, LLM gateway. This page covers its npm package (@clusteragent/cluster-mcp).

### Is the dev.clusteragent/cluster-mcp server safe to use?

dev.clusteragent/cluster-mcp scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 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 dev.clusteragent/cluster-mcp server expose?

dev.clusteragent/cluster-mcp exposes 36 tools: get_quotes, get_movers, get_news, get_chart, get_index, and 31 more. Their descriptions and schemas cost roughly 1,772 tokens of context every time the server is loaded.

### Is the dev.clusteragent/cluster-mcp server still maintained?

dev.clusteragent/cluster-mcp is still listed as active in the MCP registry. We last reached this channel on 25 September 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 dev.clusteragent/cluster-mcp server under?

dev.clusteragent/cluster-mcp 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/@clusteragent/cluster-mcp
- Socket report: https://socket.dev/npm/package/@clusteragent/cluster-mcp
- Repository: https://github.com/clusteragent/cluster
- Changelog RSS feed: https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/clusteragent-cluster-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/clusteragent-cluster-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-clusteragent-cluster-mcp/clusteragent-cluster-mcp