mcpField
P
pentagonal-mcp

pentagonal-mcp

Local
github.com/Pentagonal-aiSecurity1Updated 13w ago

About pentagonal-mcp

pentagonal-mcp connects MCP clients to Pentagonal’s smart contract tools for token research, security audits, contract generation, fixes, and compilation. It covers Solidity and Anchor/Rust, with support for eight listed blockchains.

Key features

  1. 01Token and contract intelligence
  2. 02Eight-agent security audits
  3. 03Generate Solidity and Anchor/Rust
  4. 04Fix identified vulnerabilities
  5. 05Compile Solidity and estimate gas
  6. 06List chains and security rules

Use cases

  1. 01Inspect a token’s price and holders
  2. 02Audit a contract and review findings
  3. 03Generate a contract from a description
  4. 04Compile Solidity and review gas estimates

MCP support

Exposes Pentagonal’s contract research, auditing, generation, repair, compilation, and reference tools to MCP clients. The README shows stdio and HTTP connection options.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"achilles1089-pentagonal": {
"command": "npx",
"args": [
"-y",
"pentagonal-mcp"
],
"env": {
"PENTAGONAL_API_KEY": "<PENTAGONAL_API_KEY>"
}
}
}
}
Run commandnpx -y pentagonal-mcp
Environment variables to set
PENTAGONAL_API_KEYSecretPentagonal API key (optional — free tools work without it, paid tools accept x402 USDC on Base)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmpentagonal-mcp1.0.1

Tools

7

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
chainenumNoTarget blockchainethereum | polygon | arbitrum | base | optimism | bsc | avalanche | solana
promptstringYesNatural language description of the smart contract to generate. Be specific about features, access control, and tokenomics.
solana_typeenumNoFor Solana only: "program" for Anchor/Rust programs, "token" for SPL token JSON configprogram | token
use_learned_rulesbooleanNoInject self-learning security rules into generation prompt

Details

From the project README

pentagonal-mcp

pentagonal MCP server npm License: MIT

MCP server for Pentagonal — the AI-powered smart contract forge.

Tools

ToolDescriptionAuth
pentagonal_lookupToken intelligence — price, holders, LP lock, honeypot, source codeFree (rate limited)
pentagonal_audit8-agent security pen test with severity grouping and PoC exploits$5 (credit or x402)
pentagonal_generateGenerate contracts from natural language (Solidity + Anchor/Rust)$5 (credit or x402)
pentagonal_fixFix a specific vulnerability while preserving functionalityFree (rate limited)
pentagonal_compileCompile Solidity to ABI + bytecode + gas estimatesFree (rate limited)
pentagonal_rulesView accumulated self-learning security rulesFree
pentagonal_chainsList all supported blockchainsFree

Supports Ethereum, Base, Polygon, Arbitrum, Optimism, BSC, Avalanche, and Solana.

Setup

Claude Desktop (stdio)

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "pentagonal": {
      "command": "npx",
      "args": ["-y", "pentagonal-mcp"],
      "env": {
        "PENTAGONAL_KEY": "your-api-key"
      }
    }
  }
}
Claude Code / Cursor / Windsurf (HTTP)

Add to your MCP config:

{
  "mcpServers": {
    "pentagonal": {
      "type": "http",
      "url": "https://www.pentagonal.ai/api/mcp",
      "headers": {
        "x-pentagonal-api-key": "your-api-key"
      }
    }
  }
}

Get an API Key

  1. Sign in at pentagonal.ai
  2. Click your avatar → 🔑 API Keys
  3. Generate a key — it's shown once, copy it immediately

Payment Options

  • Credits — $5 per audit or generate, buy via the web app (EVM or Solana)
  • x402 — agents pay per-use with USDC on Base (no account needed)
  • API key — use your credit balance programmatically
  • Free tools — fix, compile, lookup, rules, chains are free for everyone

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.