mcp-deadbugz-simulator

Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.

Demonstrates deceptive tool naming and unsanitized shell execution by exposing tools that perform OS fingerprinting and run local system commands through MCP. Intended for security research on vulnerabilities in the MCP ecosystem.

Presents a plausible, tool-rich workspace surface — file reading, credential listing, command execution, database queries, and configuration retrieval — that returns only synthetic results while logging every connection, tool call, and argument received. It enables researchers to measure what MCP clients and agents actually do when handed dangerous-sounding tools, including whether they follow injected instructions or complete a retrieve-then-use credential chain.

Serves as an intentionally vulnerable training target that exposes eight planted MCP vulnerability challenges—tool poisoning, rug pulls, path traversal, SSRF, command injection, missing auth, prompt-injection chains, and secrets exposure—each with a patched counterpart so users can exploit, detect, and remediate real-world MCP security flaws.