Docs & AI · Official remote MCP server

The Agentrisk MCP server,
connected in one click.

Pre-trade token risk scoring API for Base tokens, paid via x402. Connect the official Agentrisk MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.

Connect Agentrisk free How it works

Free to start · No credit card · No hosting needed

Use this server

Add Agentrisk to your AI in one minute

Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.

claude mcp add --transport http agentrisk https://agentrisk.dev/mcp/manifest

Run in your terminal, then restart Claude Code.

Agentrisk · https://agentrisk.dev/mcp/manifest

What you can do

What your AI can do with Agentrisk

Real prompts you can type the moment it's connected — no setup, no docs to read.

“Use “check_token_risk”: Checks whether a token on Base is safe enough for an autonomous agent to trade. Returns riskScore, riskLevel, and shouldExecute with structu.”

Security check

How secure is the Agentrisk MCP server?

Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how Agentrisk holds up.

✓ Verified directory serverAgentrisk · agentrisk.dev

Official endpoint

Operated by Agentrisk (agentrisk.dev) at its documented MCP endpoint — not a third-party mirror or community re-host.

No sign-in needed

This server only exposes public data — no account and no credentials are involved when you connect.

Scanned before it goes live

gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.

Watched for drift

If Agentrisk adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.

Run the free scanner on Agentrisk's server →

How it works

Connected in three steps

Connect your gate

Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.

Pick Agentrisk

Choose Agentrisk in the gate directory. No sign-in needed.

Use it anywhere

Agentrisk's tools are live in every AI client you've connected — with rules and logging built in.

Connect Agentrisk free

Free to start · No credit card · No hosting needed

Straight from the server

The actual tools Agentrisk exposes

Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.

check_token_risk — Checks whether a token on Base is safe enough for an autonomous agent to trade. Returns riskScore, riskLevel, and shouldExecute with structu

Author

Who runs the Agentrisk MCP server?

agentrisk.dev

More servers from agentrisk.dev →

Own this server? Claim the listing →

Server facts

The Agentrisk MCP server at a glance

Endpointhttps://agentrisk.dev/mcp/manifest

Operated byAgentrisk (agentrisk.dev)

CategoryDocs & AI

Sign-inNone — public data only

Available in gateYes — one-click connect

Works withClaude, ChatGPT, Cursor & any MCP client

FAQ

Questions, answered

Is there an official Agentrisk MCP server?

Yes — Agentrisk operates its own remote MCP server at agentrisk.dev. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.

How do I connect Agentrisk to Claude or ChatGPT?

Add gate's gateway URL to your AI client once, then pick Agentrisk in the directory. No account or sign-in is needed. From then on, Agentrisk's tools are available in every client you've connected to gate.

Do I need to host anything?

No. Agentrisk runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.

Is the Agentrisk MCP server safe to connect?

It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.