Deception Remote MCP Server
Simulates an Okta admin password reset tool for deception-based honeypot detection.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Threat Trap
A decoy MCP server on Cloudflare Workers. It exposes a fake internal admin tool (an Okta password reset) next to harmless tools. Legitimate users have no reason to call the admin tool, so any call to it is a detection signal. Each call fires a Canarytoken alert.
It is the reference decoy for the paper Deception at the Registry Layer, which covers placing decoy servers alongside real ones in an MCP registry.
Live instance: deception-remote-mcp-server.harshad-surfer.workers.dev (MCP endpoint: /mcp)
Tools
Tool | Role | Fires the canary |
| Lists the available tools | No |
| Q&A over placeholder profile data, so the server looks like a real personal assistant | No |
| Trap. Pretends to reset a user's password, and answers differently for privileged names such as | Yes |
The trap is also reachable as a plain REST endpoint (POST /okta_admin_password_reset), which catches scanners that skip MCP.
Related MCP server: G4 Data Model MCP Server
Endpoints
Path | Transport |
| Streamable HTTP (current MCP transport) |
| Server-Sent Events (legacy transport) |
| Landing page for browsers; MCP requests sent here are routed to |
| REST trap ( |
Deploy your own
Or deploy manually:
npm install
npm run deployAlerts go to the Canarytoken URL in CANARY_TOKEN_URL at the top of src/index.ts. Before deploying your own copy, create a free Web bug / URL token at canarytokens.org and replace that URL with yours. Otherwise your alerts go to the original author.
Connect a client
Clients that support remote MCP servers (Cursor, Windsurf, Claude Desktop and others) take a config like this:
{
"mcpServers": {
"threat-trap": {
"url": "https://<your-worker>.workers.dev/mcp"
}
}
}For clients that only support local (stdio) servers, bridge with mcp-remote:
{
"mcpServers": {
"threat-trap": {
"command": "npx",
"args": ["mcp-remote", "https://<your-worker>.workers.dev/mcp"]
}
}
}To test whether your own agent takes the bait, connect it to your deployment and give it an open-ended task. Then check whether the canary fired.
Detection data
Each alert carries the tool name, the username the caller asked to reset, a timestamp, and, for REST calls, the caller's IP and User-Agent. The same fields are written to the Worker log. Requests are rate-limited per IP (5 per minute on the REST endpoint).
Testing
test-live-honeypot.sh and owasp-ai-security-attack.js send scripted rogue-agent requests. Both target BASE_URL, so edit that to point at your own deployment. Each trap call fires your canary. To test without real alerts, point CANARY_TOKEN_URL at a local listener and run against npm run dev.
Related
KubeTrap: a Kubernetes access-portal decoy with DNS and webhook tripwires
Project page: harshadsadashivkadam.com/projects/mcp-threat-trap
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Cloudflare Workers MCP server: ai-agent-scratchpad
Cloudflare Workers MCP server: agent-workflow-engine
Zero-dependency Cloudflare Worker gateway turning websites and REST APIs into MCP tools.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA serverless MCP implementation on Cloudflare Workers that allows deploying custom AI tools without authentication requirements.-
- FlicenseNot gradedqualityDmaintenanceEnables deployment of a customizable MCP server on Cloudflare Workers without authentication. Allows users to define custom tools and connect to clients like Claude Desktop or Cloudflare AI Playground for remote tool execution.-
- AlicenseNot gradedqualityBmaintenanceEnables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables defenders to deploy a deception-driven MCP honeypot that records attacker tool calls, issues attributable canary secrets, fingerprints AI agents, and feeds signed alerts to a Blue Team responder for one-click or automatic containment.3Apache 2.0