Browse
→ AI & Models
→ ToolQuest MCP
ToolQuest MCP
Deterministic escape-room benchmark server for tool-using agents, exposed through local stdio MCP. It provides puzzle rooms with strict machine-readable tool results, isolated runs, state versions, idempotency keys, replay verification, JSONL traces, Markdown reports, and no LLM judge or external service requirement. Public GitHub repository created September 2, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | npx -y toolquest-mcp |
| Install | npx -y toolquest-mcp |
Use Cases
| 01 | Evaluate how tool-using agents explore deterministic puzzle rooms through MCP tools |
| 02 | Record reproducible JSONL traces and export Markdown reports for benchmark runs |
| 03 | Test retry safety, state-version handling, and long-horizon tool planning without an LLM judge |
Tags
agent-evaluation benchmark tool-use escape-room deterministic traces replay typescript
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>