Koskamo

PickleCheck MCP

Provides three safety checks for AI trading agents on Base: scam checks for Base tokens and wallets, endpoint checks for x402 services, and payment verification across multiple chains. It offers daily free calls and uses USDC on Base for subsequent payments via x402.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

PickleCheck MCP logo, by PickleCheckCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by PickleCheck
MCP endpoint (Streamable HTTP)
https://picklecheck.onrender.com/mcp
Vendor documentation

What you can do with it

  • Check if a Base token is a rug, honeypot, or insider dump
  • Verify if an x402 endpoint is safe to pay
  • Confirm if a payment transaction landed on-chain
  • Check wallet safety against sanctions and blacklists

Source and maintenance

Community listingRegistry 1.0.0

Protocol and capabilities

Server
picklecheck 1.0.0
MCP protocol
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

PickleCheck: scam, endpoint and payment safety checks for AI trading agents on Base. null means unknown, never safe. A few free calls a day per IP, then x402 pay-per-call: a tool result with isError and a PaymentRequired object means pay it and retry the same call with _meta["x402/payment"]. No x402 wallet in your client? That result also says how to pay the same call over HTTP. Results are facts, not financial advice.

Tools

3 advertised

scam_check — Scam check
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Check a Base token (0x address) or URL for scam and rug risk before buying, or a wallet against the sanctions, USDC-blacklist and known-scam-deployer lists. Returns action OK | CAUTION | AVOID | VERIFY_MORE with the facts behind it and a ready-to-show summary. null means unknown, never safe. Free: 3 a day per IP (counted across the HTTP routes and MCP), then $0.008 per call via x402.

scam_check input schema
{
  "type": "object",
  "required": [
    "target"
  ],
  "properties": {
    "quick": {
      "type": "boolean",
      "description": "Faster check (about 5 s) with fewer facts; skipped facts are null"
    },
    "target": {
      "type": "string",
      "description": "Base 0x token address, wallet address or URL"
    },
    "compact": {
      "type": "boolean",
      "description": "No summary text, no disclaimer, no null fields"
    },
    "amount_usd": {
      "type": "number",
      "description": "Your trade size in USD: adds a sell quote at that size (fields.sell_at_size) and the price impact"
    }
  }
}
scam_check annotations
{
  "title": "Scam check",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
endpoint_check — x402 endpoint check
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Check whether an x402 endpoint is safe to pay: it looks at what the endpoint asks you to pay and to whom and compares that with its history. It never pays the endpoint. Unreachable endpoints and bad input are not charged. Free: 1 a day per IP (counted across the HTTP routes and MCP), then $0.005 per call via x402.

endpoint_check input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "https URL of the x402 endpoint"
    }
  }
}
endpoint_check annotations
{
  "title": "x402 endpoint check",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
verify_payment — Payment check
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Verify an on-chain payment from its transaction hash on Base, Ethereum, Arbitrum, Solana or Bitcoin (chain is detected if omitted). Returns status and verified. pending, unknown and not_found answers are not charged. Free: 1 a day per IP (counted across the HTTP routes and MCP), then $0.003 per call via x402.

verify_payment input schema
{
  "type": "object",
  "required": [
    "tx_hash",
    "expected_amount",
    "receiver"
  ],
  "properties": {
    "chain": {
      "enum": [
        "base",
        "ethereum",
        "arbitrum",
        "solana",
        "bitcoin"
      ],
      "type": "string",
      "description": "Omit to auto-detect"
    },
    "exact": {
      "type": "boolean"
    },
    "token": {
      "type": "string",
      "description": "Symbol or contract/mint; default USDC (EVM), SOL, BTC"
    },
    "tx_hash": {
      "type": "string"
    },
    "receiver": {
      "type": "string"
    },
    "not_before": {
      "type": "string",
      "format": "date-time"
    },
    "expected_from": {
      "type": "string"
    },
    "expected_amount": {
      "type": "string",
      "description": "Decimal string, human units"
    },
    "min_confirmations": {
      "type": "integer",
      "description": "Can raise, not lower, the chain default"
    }
  },
  "description": "Aliases accepted: network=chain, amount=expected_amount, to|recipient|payTo=receiver, asset=token, txid|signature|hash=tx_hash, from|sender=expected_from"
}
verify_payment annotations
{
  "title": "Payment check",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
571 ms
95th percentile latency
571 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 571 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http picklecheck-mcp https://picklecheck.onrender.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add picklecheck-mcp --url https://picklecheck.onrender.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable picklecheck-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "picklecheck-mcp": {
      "url": "https://picklecheck.onrender.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "picklecheck-mcp": {
      "type": "streamableHttp",
      "url": "https://picklecheck.onrender.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start picklecheck-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "picklecheck-mcp": {
      "type": "http",
      "url": "https://picklecheck.onrender.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http picklecheck-mcp https://picklecheck.onrender.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "picklecheck-mcp": {
      "url": "https://picklecheck.onrender.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "picklecheck-mcp": {
      "serverUrl": "https://picklecheck.onrender.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like PickleCheck MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.