scry-mcp

MCP serverDev tools

Find out whether an IPv4 address has been linked to attacker activity, straight from your AI. scry is a free integration that looks up IPv4 addresses against a distributed corpus of attacker observations. Once added, your AI can check and summarize addresses whenever you ask.

Use scry-mcp in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add scry-mcp and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the scry stats tool from scry-mcp

Details

Available today. Use it from your connected AI after setup.

After adding scry, share an IPv4 address with your AI and ask it to look it up. Addresses from a recent alert or log entry are a good place to start.

scry-mcpStart free

What your AI can do with it

  • Look up any IPv4 address on request
  • Check whether an address has been observed in attacker activity
  • Investigate suspicious IP addresses from logs or alerts you share
  • Summarize what the observation corpus shows about an address
  • Run lookups at no cost

Install scry-mcp

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user scry-mcp 'https://mcp.tunnelmind.ai/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.tunnelmind.ai/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=scry-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC50dW5uZWxtaW5kLmFpL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.tunnelmind.ai/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add scry-mcp --url 'https://mcp.tunnelmind.ai/mcp'

    Run it once, then sign in with codex mcp login scry-mcp if the server asks for an account.

From the project's README

As published by tunnelmind/scry-mcp in README.md.

MCP (Model Context Protocol) server for the Scry corpus. Wraps the scry-api public endpoints as agent-callable tools.

Hosted at mcp.tunnelmind.ai. MCP spec version 2025-03-26. Streamable HTTP transport.

Tools (v0.1)

ToolWrapsTier
scry_checkGET /v1/check/{ip}Free

Future tools (deferred to defender tier; need ATAP attestation):

  • scry_watch — subscribe to state changes for an IP/domain
  • scry_actor — full actor profile
  • scry_campaign — campaign detail

Wire protocol

POST https://mcp.tunnelmind.ai/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"initialize"}

Methods:

  • initialize — handshake, returns { protocolVersion, capabilities, serverInfo }
  • notifications/initialized — client → server notification (returns 204)
  • tools/list — returns { tools: [...] }
  • tools/call — { name, arguments } → { content: [{ type: "text", text }] }
  • ping — returns {}

Discovery:

GET https://mcp.tunnelmind.ai/
→ { service, version, protocol, transport, endpoint, tools }

Layout

src/
  worker.js   transport (JSON-RPC 2.0 over POST /mcp)
  tools.js    tool definitions + handlers
test/
  tools.test.js   unit tests for tool registry

Setup

npm test
npx wrangler deploy

No bindings, no secrets — this Worker is a thin proxy with no state.

Tools it offers (12)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • scry_stats
  • scry_check
  • scry_check_bulk
  • scry_top
  • scry_timeseries
  • scry_asn
  • scry_country
  • scry_tools
  • scry_tool
  • scry_campaigns
  • scry_campaign
  • scry_recent

Signals

Last commit
May 2026

Ahel review (caution)

  • S3medium
    repository is archived

Automated review, not a security audit. Ruleset v1.

Advanced
Delivery
scry MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
ai-tunnelmind-scry
Source
github.com/tunnelmind/scry-mcp
Hosted endpoint
https://mcp.tunnelmind.ai/mcp