TokenGuard

Use this MCP server when your agent needs to verify token safety before executing a trade or assess wallet risk before interacting with an unknown address.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Check Token Safety: Full token safety analysis. Returns a risk score (0-100, lower is safer), a SAFE / CAUTION / AVOID recommendation, a confidence level, and three sub-checks: deployer wallet age in
  • Check Token Safety Lite: Fast token pre-trade check — deployer wallet age and LP lock status only, no holder concentration analysis. Typically completes in under 3 seconds. Returns risk score, SAFE /
  • Check Wallet: Full wallet intelligence profile for any EVM address. Returns a CLEAN / SUSPICIOUS / FLAGGED verdict, composite risk score (0-100), whale/mid/retail classification by holdings, bot likel

What data it sees

Do you need an account

No: the server works without sign-in

Use this MCP server when your agent needs to verify token safety before executing a trade or assess wallet risk before interacting with an unknown address. Covers Solana/Pump.fun (474ms p50), Base, Ethereum, and Arbitrum. No API keys — pay per query in USDC on Base via x402. Tools: check_pump_token (Pump.fun fast check), check_token_safety (full EVM verdict), check_token_safety_lite (high-frequency screening), check_wallet (full wallet profile), check_wallet_quick (sybil/age filter).

How to connect

How to connect TokenGuard to Claude

The server address to paste into Claude settings:

https://baseguard-walletguard--riamsantky.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 TokenGuard to ChatGPT

The server address to paste into ChatGPT settings:

https://baseguard-walletguard--riamsantky.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 TokenGuard to Cursor

The server address to paste into Cursor settings:

https://baseguard-walletguard--riamsantky.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 (4)

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

check_token_safetyFull token safety analysis. Returns a risk score (0-100, lower is safer), a SAFE / CAUTION / AVOID recommendation, a confidence level, and three sub-checks: deployer wallet age in days, whether the liquidity pool is locked, and top-10 holder concentration percentage. Use this before trading or listing any token. Supports Base, Ethereum, Arbitrum, and Solana. Results cached 4 hours.
check_token_safety_liteFast token pre-trade check — deployer wallet age and LP lock status only, no holder concentration analysis. Typically completes in under 3 seconds. Returns risk score, SAFE / CAUTION / AVOID recommendation, deployer age in days, and LP lock flag. Use this when screening many tokens quickly. For full holder analysis use check_token_safety.
check_walletFull wallet intelligence profile for any EVM address. Returns a CLEAN / SUSPICIOUS / FLAGGED verdict, composite risk score (0-100), whale/mid/retail classification by holdings, bot likelihood score (0-100), contract deploy count as a rug-pull proxy, active chains, wallet age in days, transaction count, and risk flags such as NEW_WALLET, HIGH_BOT_SCORE, MIXER_INTERACTIONS, and SERIAL_DEPLOYER. Use this to evaluate token deployers, counterparties, or airdrop claimants. Cached 1 hour.
check_wallet_quickFast wallet check — wallet age in days and outgoing transaction count only. Typically completes in under 2 seconds. Returns a simple CLEAN / SUSPICIOUS verdict alongside age and tx count. Use this when confirming a wallet is not brand-new before a quick trust decision, such as filtering obvious sybils in an airdrop. For full risk profiling including bot score, classification, and rug history use check_wallet.