Freysa Security

Token security intelligence for autonomous AI agents.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Security.Trial: 3 free security/reasoning calls per day per wallet. No payment needed. Try security.score, security.honeypot, or security.address.
  • Security.Score: Quick token security score 0-100. Returns SAFE/CAUTION/DANGER decision plus risk flags. Fastest decision — $0.01. For agents that need one number before trading.
  • Security.Honeypot: Check if a token is a honeypot. Uses real eth_call sell simulation to detect if you can actually sell the token. Returns sell restrictions, buy/sell tax, blacklist status, and evide

What data it sees

Do you need an account

No: the server works without sign-in

Token security intelligence for autonomous AI agents. On-chain honeypot detection, contract risk analysis, wallet forensics, and transaction simulation. Pay-per-call via x402 on Base. Deterministic — no AI hallucination.

How to connect

How to connect Freysa Security to Claude

The server address to paste into Claude settings:

https://freysa--feraxe727.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Freysa Security to ChatGPT

The server address to paste into ChatGPT settings:

https://freysa--feraxe727.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Freysa Security to Cursor

The server address to paste into Cursor settings:

https://freysa--feraxe727.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

security.trial3 free security/reasoning calls per day per wallet. No payment needed. Try security.score, security.honeypot, or security.address.
security.scoreQuick token security score 0-100. Returns SAFE/CAUTION/DANGER decision plus risk flags. Fastest decision — $0.01. For agents that need one number before trading.
security.honeypotCheck if a token is a honeypot. Uses real eth_call sell simulation to detect if you can actually sell the token. Returns sell restrictions, buy/sell tax, blacklist status, and evidence with block number. Deterministic — no AI hallucination.
security.addressCheck if a wallet address is safe. Returns scam indicators, risk score (0-100), and recommendation. Checks sanction lists, phishing links, suspicious patterns. Used by trading agents before sending funds.
security.walletDeep wallet forensic audit. Traces on-chain history, flags suspicious patterns, identifies scam links, MEV activity, and money flow patterns. Returns structured risk score with evidence chain.
security.approvalCheck if a token approval is safe. Analyzes approve/approveForAll transactions for dangerous spenders, unlimited allowance risks, and malicious patterns. Every output cites block evidence.
security.contractSmart contract risk assessment. Checks if verified, upgradeable, has dangerous functions, proxy patterns, owner privileges, and known exploit vectors. Deterministic on-chain analysis.
security.buy_decisionBUY/AVOID/CAUTION decision for any token. Combines honeypot check, contract risk, liquidity analysis, and holder concentration. Returns structured decision with confidence score and evidence.
security.pre_tradeComplete pre-trade risk assessment. Checks token, contract, wallet, liquidity, slippage, and price impact in one call. Includes amount-based impact calculation. For agents that need to know: is this trade safe?
security.preflightOne-call comprehensive safety check for AI agents. Checks target contract, token, and wallet together. Returns PROCEED/CAUTION/ABORT decision with evidence. Designed for autonomous agents executing complex workflows.