MCP.Market

Pentagonal MCP server

by Achilles1089·io.github.Achilles1089/pentagonal-mcp·v1.0.1·1 stars
No reviews yet

AI smart contract forge — 8-agent security audits, generation, and compilation across 8 chains

B72/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B72/100

full report

Adoption
Growing

1 stars53 downloads/wk

Reviews

Write one

Nobody has reviewed Pentagonal yet.

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

Pentagonal tools (7, 1 write)

write = sends, deletes, buys or posts

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

  • pentagonal_auditwrite action

    Run an 8-agent security pen test on a smart contract. Each agent specializes in a different attack vector: reentrancy, flash loans, access control, gas griefing, oracle manipulation, front-running, integer overflow, and economic exploits. Findings are returned with severity ratings and line numbers. New security rules are automatically learned from each audit.

  • pentagonal_chains

    List all supported blockchains with their chain IDs, explorer URLs, and deployment hints.

  • pentagonal_compile

    Compile Solidity source code and return the ABI, bytecode, constructor arguments, and gas estimates. Use this after generating and auditing a contract to prepare it for deployment.

  • pentagonal_fix

    Fix a specific vulnerability in a smart contract. Provide the contract code and the finding details — returns the complete fixed contract preserving all existing functionality.

  • pentagonal_generate

    Generate a production-quality smart contract from a natural language description. Supports EVM (Solidity) and Solana (Anchor/Rust or SPL Token config). The generator uses Pentagonal's self-learning security rules to produce safer code.

  • pentagonal_lookup

    Look up any token or smart contract by address. Returns the full intelligence report: price, market cap, ATH, 24h volume, transactions, holders, liquidity, LP lock status, pool count, security flags (honeypot, mintable, pausable, hidden owner, taxes), social links, and source code if verified. Use this before auditing to understand the full token landscape. Supports EVM and Solana tokens.

  • pentagonal_rules

    Get the current self-learning security rules. These rules are accumulated from every audit Pentagonal performs — the more contracts audited, the smarter the system gets.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan13 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 62 days ago12/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Pentagonal compares

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

Safety score
72/100
higher than 40% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,711 AI and agents servers
Downloads a week
53
more than 44% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 1 change

Install Pentagonal in Claude Code, Cursor or VS Code

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

claude mcp add pentagonal-mcp -- npx -y pentagonal-mcp
Add to Cursor

What the publisher says

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

Pentagonal

AI-powered smart contract forge with an 8-agent adversarial security audit system.

Generate, audit, fix, and compile Solidity and Anchor/Rust contracts across 8 chains including Ethereum, Base, Polygon, Arbitrum, Optimism, BSC, Avalanche, and Solana. Includes token intelligence lookups with market data, holder analysis, and honeypot detection. Self-learning security rules engine that improves with every audit.

MCP Server

Install via npm:

npx pentagonal-mcp

Claude Desktop

Add to claudedesktopconfig.json:

{
  "mcpServers": {
    "pentagonal": {
      "command": "npx",
      "args": ["-y", "pentagonal-mcp"],
      "env": {
        "PENTAGONAL_KEY": "your-api-key"
      }
    }
  }
}

HTTP (Claude Code / Cursor / Windsurf)

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

Tools

Payment

  • 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 work for everyone

Links

  • pentagonal.ai
  • npm
  • Smithery
  • ClawHub
  • @Pentagonalai

License

MIT

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

Pentagonal: common questions

Is Pentagonal MCP server safe?
Mostly: it is graded B (72/100). Read the Pentagonal safety report
How do I install Pentagonal?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Pentagonal need an API key?
Yes. The registry entry asks for PENTAGONAL_API_KEY.
Is Pentagonal maintained?
The last commit was 100 days ago (2026-07-27). The latest release is v1.0.1.
What can I use instead of Pentagonal?
Servers from other publishers that do the same job: three.ws Provenance MCP server, LLM Sandbox MCP server and HOL Guard MCP server.
How does Pentagonal compare with other AI and agents MCP servers?
safety score 72/100 (higher than 40% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Pentagonal

Same job from other publishers: the closest match first, then the best rated.

  • three.ws Provenance
    Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
    More from nirholas →
    B
  • LLM Sandbox
    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • DCC-MCP Core
    Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
    A
  • Image
    AI image generation and editing with prompt optimization and quality presets
    B