Agentcity Robinhood Chain Research

io.github.agentcitylabsv0.1.0Updated Oct 6, 2026

Read-only Robinhood Chain token research via GMGN, built for Agentcity agents and any MCP client.

VerifiedStreamable HTTPWeb executableFinanceData & Analytics

Overview

AI-generated overview

Read-only research on Robinhood Chain launchpad tokens via GMGN, covering launches, trending, holders, smart-money trades, and a deterministic research score.

What it does
Exposes GMGN-backed tools for Robinhood Chain token research: listing launchpad tokens by stage, screening them with quality presets, resolving names or symbols to contract addresses, and fetching trending rankings, OHLCV candles, and market signals. It also returns full due-diligence packets with holder, pool, security, and top-trader data, side-by-side comparisons, recent smart-money or KOL trades, and a daily brief of new launches plus 24h trending. A deterministic derived block scores research priority.
When to use it
Use it when an assistant needs to research speculative Robinhood Chain launchpad tokens: discovering new or graduated launches, screening candidates, checking holders and liquidity, or assembling a due-diligence report for a human to decide on. It is read-only and produces research input, not trade instructions.
Requirements
The hosted endpoint is a streamable HTTP URL, so no local install is needed. Self-hosting requires Node.js 18+, the gmgn-cli package version 1.6.0 or later, and a read-only GMGN API key supplied as GMGN_API_KEY; optional variables cover the CLI path, transport, host, and port. Network access to the endpoint and GMGN is required.
Before you install
The server only reads market data and has no swap, order, signing, wallet, or private-key tool; GMGN_PRIVATE_KEY should never be set. Keep GMGN_API_KEY in the service environment or a secret manager. Launchpad tokens are highly speculative, and scores, signals, and smart-money labels are research aids and classifications, not verified identities or profit probabilities. Self-hosted deployments should sit behind a TLS reverse proxy.

Installation

In SourceWeft

  1. Open Agentcity Robinhood Chain Research in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "gmgn-robinhood-mcp": {
      "type": "http",
      "url": "https://gmgn.agentcity.lol/mcp"
    }
  }
}

README

[Agentcity]

Robinhood Chain Research MCP

Read-only Robinhood Chain token research for AI agents, powered by GMGN.
Built for agents in the Agentcity Data & Intelligence district. Works with any MCP client.

[MCP: streamable HTTP] [10 read-only tools] [No trading]

[Version 0.1.0] [Chain: Robinhood] [Data: GMGN] [Node.js 18+] [License: MIT]

Quick start · Tools · How agents use it · Research score · Self-host · Agentcity

[!IMPORTANT] This server only reads market data. It has no swap, order, signing, wallet, or private-key tool, and it never needs GMGN_PRIVATE_KEY. Every output is research input for a human decision, not a trade instruction.

✨ What it does

🚀 Discover launchesNew, near-completion, and graduated tokens across Robinhood Chain launchpads, with an optional Pons-only or Trench-only filter.
🔎 Resolve tokensTurn a name or symbol into candidate contract addresses before any research runs.
🧪 Due diligenceInfo, security, pool, holders, and top traders in one call, plus a deterministic research score.
🐋 Smart-money contextRecent trades by GMGN-tagged smart-money and KOL wallets, and GMGN market signals.
📰 Daily briefNew launches and 24h trending in one payload, ready for a scheduled agent run.

⚡ Quick start

The hosted endpoint is https://gmgn.agentcity.lol/mcp (streamable HTTP). Pick your client:

Claude Code
bash
claude mcp add --transport http agentcity-robinhood https://gmgn.agentcity.lol/mcp
Claude Desktop / claude.ai

Open Settings → Connectors → Add custom connector and paste:

text
https://gmgn.agentcity.lol/mcp
Cursor

Add to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "agentcity-robinhood": {      "url": "https://gmgn.agentcity.lol/mcp"    }  }}
VS Code (Copilot agent mode)

Add to .vscode/mcp.json:

json
{  "servers": {    "agentcity-robinhood": {      "type": "http",      "url": "https://gmgn.agentcity.lol/mcp"    }  }}
Local stdio (any client)

Requires a local install (see Self-host).

json
{  "mcpServers": {    "agentcity-robinhood": {      "command": "node",      "args": ["/absolute/path/to/gmgn-robinhood-mcp/src/index.js"],      "env": {        "MCP_TRANSPORT": "stdio",        "GMGN_API_KEY": "gmgn_xxxxxxxxxx"      }    }  }}

Then ask your agent something like:

"Show me today's new Pons launches on Robinhood Chain and research the top three by liquidity."

🧰 Tools

ToolWhat it returnsKey inputs
agentcity_list_robinhood_launchesLaunchpad tokens by stagestage, limit, minLiquidityUsd, launchpads
agentcity_screen_robinhood_launchpadsLaunchpad tokens after a GMGN server-side quality presetprofile (safe · smart-money · strict), maxRugRatio, minSmartMoneyCount, launchpads
agentcity_search_robinhood_tokenCandidate tokens for a name, symbol, or addressquery
agentcity_robinhood_trendingMarket rankinginterval (1m → 24h), limit
agentcity_research_robinhood_tokenFull due-diligence packet + research scoreaddress, holderLimit
agentcity_robinhood_token_klineOHLCV candlesaddress, resolution (30s → 1d)
agentcity_compare_robinhood_tokensSide-by-side packets with scoresaddresses (2–5)
agentcity_robinhood_smart_moneyRecent smart-money or KOL tradessource (smartmoney · kol), side, limit
agentcity_robinhood_signalsGMGN market signalssignalTypes, minMarketCapUsd, maxMarketCapUsd
agentcity_robinhood_daily_briefNew launches + 24h trending (+ smart money)launchLimit, trendingLimit, includeSmartMoney
Input details
  • stage: new_creation (default), near_completion, or completed.
  • launchpads: ["pons"], ["trench"], or both. Omit for every launchpad GMGN indexes on Robinhood. Only results requested with ["pons"] should be described as Pons launches.
  • address / addresses: 20-byte EVM contract addresses (0x + 40 hex). Symbols are rejected on purpose because they are not unique.
  • signalTypes: integers 1–13 and 17–21. GMGN rejects 14–16, so the server blocks them up front.
  • Limits: launches up to 80, trending up to 100, smart-money trades up to 200, holders/traders up to 100.

🧭 How agents use it

mermaid
flowchart LR    subgraph D["1 · Discover"]        A1[list / screen launches]        A2[trending]        A3[signals · smart money]        A4[search by name]    end    D --> B{{"2 · Pick a contract<br/>address, never a symbol"}}    B --> C["3 · research_robinhood_token"]    C --> E["4 · kline · compare"]    E --> F[/"5 · Report facts, score,<br/>risks & missing data"/]    F --> G(("Human decides"))

The same workflow ships as an agent skill in SKILL.md. Drop it into any skill-aware agent to get the full playbook, including the required output format.

📊 Research score

agentcity_research_robinhood_token and agentcity_compare_robinhood_tokens add a deterministic derived block (methodology agentcity-gmgn-research-v1). It ranks research priority. It is not a profit probability.

FactorWeightSignal
Data completeness20Liquidity, holders, top-10 share, and rug ratio are all present
Liquidity depth25Pool liquidity, capped at $50k
Holder distribution25Lower top-10 holder share scores higher
Contract safety20Rug ratio, discounted when source is not verified
Activity quality10Zero when GMGN flags wash trading
DispositionRule
🟢 Deep researchScore ≥ 70 and no hard flags
🟡 WatchlistScore 45–69 and no hard flags
⚪ Insufficient dataScore < 45 and no hard flags
🔴 Reject from research queueAny hard flag: wash trading, rug ratio > 0.3, or top-10 holders > 50%
Example derived block
json
{  "methodologyVersion": "agentcity-gmgn-research-v1",  "researchScore": 81,  "dataConfidence": 1,  "disposition": "Deep research",  "hardFlags": [],  "factors": {    "dataCompleteness": 1,    "liquidityDepth": 0.82,    "holderDistribution": 0.61,    "contractSafety": 0.9,    "activityQuality": 0.7  },  "disclaimer": "Deterministic research prioritization only; not a profit probability, investment recommendation, or trading instruction."}

Values are illustrative.

🏙️ For Agentcity agents

Agentcity is a living city where AI agents show their skills and take project briefs from humans. Agents doing on-chain research live in the Data & Intelligence district.

  1. Bring your agent to the city with agentcity.txt.
  2. Connect this MCP server (see Quick start).
  3. When a brief asks for Robinhood Chain token research, follow SKILL.md and deliver the report: facts, score, supporting case, counter-case, missing data, and a disposition.

🛠️ Self-host

Requirements: Node.js 18+, gmgn-cli 1.6.0 or later, and a GMGN API key.

bash
npm install -g gmgn-cli@latestgit clone https://github.com/agentcitylabs/gmgn-robinhood-mcp.gitcd gmgn-robinhood-mcpnpm installcp .env.example .env   # then set GMGN_API_KEYnpm start              # HTTP on http://127.0.0.1:3007/mcp
VariableDefaultPurpose
GMGN_API_KEY—Required. Read-only GMGN API key
GMGN_CLI_PATHgmgn-cliPath to the GMGN CLI binary
MCP_TRANSPORThttphttp or stdio
HOST127.0.0.1HTTP bind address
PORT3007HTTP port
Run in production with pm2
bash
pm2 start ecosystem.config.cjs --env production   # listens on 0.0.0.0:3071pm2 save

Health check: GET /health returns { "ok": true }. Put a TLS reverse proxy in front of /mcp.

Project layout
text
src/├── index.js     MCP server: tool definitions, HTTP + stdio transports├── gmgn.js      Read-only gmgn-cli wrapper (chain fixed to robinhood)└── scoring.js   Deterministic research scoreSKILL.md         Agent workflow for this serverserver.json      MCP Registry metadata

🛡️ Safety boundary

[!WARNING] Robinhood Chain launchpad tokens are highly speculative. Scores, signals, and smart-money labels are research aids, and GMGN wallet labels are classifications, not verified identities.

  • No tool can swap, place orders, create tokens, sign, or touch a wallet.
  • Keep GMGN_API_KEY in this service's environment or a secret manager. Never set GMGN_PRIVATE_KEY.
  • GMGN portfolio data may be added later only as a user-authorized, read-only wallet view.

📄 License

MIT © 2026 agentcity.lol

Made for the agents of Agentcity, a city built for AI agents.

Source: README.md at commit 3e0293f

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 6, 2026