MCP.Market

Cookin MCP server

by cookinfun·io.github.cookinfun/cookin-mcp·v0.1.1

Solana and Pump.fun token intelligence: bundles, holder quality, KOLs, deployer history.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

0 stars51 downloads/wk

Reviews

Write one

Nobody has reviewed Cookin yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cookin tools (8)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • deployer_history

    Every token one deployer has launched, with its bond rate, peak market

  • list_agent_buys

    Tokens the top Cookin trading agents bought most recently, with quality

  • list_graduated_tokens

    Pump.fun tokens that recently graduated to Raydium or PumpSwap, with

  • list_new_tokens

    Newly launched Pump.fun tokens that passed Cookin's rug filters, with

  • list_pumping_tokens

    Pump.fun tokens currently pumping, with quality signals, holder behavior,

  • profile_wallet

    Lifetime trading profile of one Solana wallet: PnL, ROI, win rate, hold

  • scan_token

    Full Cookin snapshot for one Solana or Pump.fun token: quality score,

  • token_trades

    Recent trades for one token, each carrying the trader's history as it

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

no findings
  • Code scan9 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 10 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Cookin compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
51
more than 43% of 12,191 servers with a package

What its tools let an agent do: 7 read · 1 run or deploy

Install Cookin in Claude Code, Cursor or VS Code

Runs npx -y @cookinfun/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add cookin-mcp -- npx -y @cookinfun/mcp
Add to Cursor

What the publisher says

From the Cookin repository's README, as published. We do not edit it. Read it on GitHub

@cookinfun/mcp

MCP server for the Cookin API: Solana and Pump.fun token intelligence for agents. Ask it who is behind a token before entering, while holding, or after exiting.

Eight tools, paid per call in USDC over x402 with no account, or covered by a Cookin Pro key.

What it answers

supply they hold, and how many of those groups are heavy net sellers.

  • Coordinated wallets. Which wallets act as one group (bundles), how much

winners, by quick sellers, by suspicious wallets, and by wallets that nuke charts when they exit.

  • Holder quality. Share of supply held by wallets that historically pick

and smart-money classification.

  • KOL positions. Which tracked KOL wallets hold, and how much.
  • Wallet reputation. One wallet's lifetime PnL, ROI, win rate, hold times,

survival curve across market cap rungs.

  • Deployer history. Every token a deployer launched, its bond rate, and a

same thresholds as the Cookin UI.

  • Ratings. A green, yellow, red or neutral verdict per metric, using the

Install

Claude Desktop

Add this to claudedesktopconfig.json:

{
  "mcpServers": {
    "cookin": {
      "command": "npx",
      "args": ["-y", "@cookinfun/mcp"],
      "env": { "SOLANA_KEY": "<base58 Solana keypair holding USDC>" }
    }
  }
}

Cursor

In .cursor/mcp.json:

{
  "mcpServers": {
    "cookin": {
      "command": "npx",
      "args": ["-y", "@cookinfun/mcp"],
      "env": { "COOKIN_API_KEY": "<Cookin Pro key>" }
    }
  }
}

Anything else that speaks MCP

SOLANA_KEY=<base58 keypair> npx -y @cookinfun/mcp

Paying

Pick one. The server prints which mode it started in, on stderr.

SOLANA_KEY is a base58-encoded 64-byte Solana keypair. The wallet needs USDC only: the facilitator pays the network fee, and a call that errors is never charged. Mint a Pro key at cookin.fun/account/api-keys.

Optional:

  • COOKINMAXPAYMENT caps what one call may pay. Default $0.05.
  • COOKINBASEURL points at another host. Default https://api.cookin.fun.

Tools

Spend less: start with one scan_token, and stop if its ratings already answer the question. fields trims a snapshot at the same price. Deployer history changes slowly, so cache it.

Remote endpoint

The same tools are served remotely at https://api.cookin.fun/mcp, with nothing to install. Point an MCP host at that URL. A tool call with no payment returns the x402 quote in its result; sign it and call again with the payment in the x_payment argument, or send a Pro key in the Authorization header.

Use the local package instead when you want the server to hold the wallet and pay for calls by itself.

Reference

  • Field-by-field reference: api.cookin.fun/skill.md
  • OpenAPI spec: api.cookin.fun/openapi.json
  • Docs: cookin.fun/api

Development

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Cookin: common questions

Is Cookin MCP server safe?
Mostly: it is graded B (82/100). Read the Cookin safety report
How do I install Cookin?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Cookin need an API key?
Yes. The registry entry asks for SOLANA_KEY, COOKIN_API_KEY.
Is Cookin maintained?
The last commit was 31 days ago (2026-10-04). The latest release is v0.1.1.
How does Cookin compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.