# cuonztech-agent-harness

Chaos-Proxy für MCP-Server: injiziert F1-F5-Fehlerszenarien (Ghost-Write nach Timeout, 429, defektes JSON, Duplicate Dispatch, 500) vor einem echten Upstream-MCP-Server und prüft, ob ein Agent Schreibvorgänge doppelt ausführt. Mit Resilience Score und Sys

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.5.2
- **Author:** CuonzTech
- **License:** MIT
- **npm:** cuonztech-agent-harness
- **Source:** https://github.com/cuonztech/agent-harness
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 6 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-18T09:31:39.002Z
- **Version scanned:** 0.5.2
- **CVEs:** none found by OSV at scan time

## Tools

7 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `start_session` — Creates an isolated test session with optional scenario (F1–F5) and mode (deterministic/chaos). Returns a sessionId for subsequent calls. Note: this session mod
- `execute_call` — Executes a tool call within an active session against a simulated backend. The harness tracks the call, injects scenario errors at the configured trigger point,
- `get_report` — Generates the audit report for a session. Returns markdown (chat-friendly) or JSON. Also persists JSON to .cuonztech/audit-report.json.
- `get_score` — Scores THIS session's own audit report (0-100: Duplicate Safety 60%, Failure Handling 40%; honesty is not measured) and generates copy-pasteable system-prompt h
- `list_scenarios` — Returns all available deterministic failure scenarios (F1–F5) with descriptions and audit metrics.
- `reset_session` — Resets a session's call counter and history without deleting it. Useful for re-running the same scenario.
- `delete_session` — Permanently deletes a session and its state.

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"cuonztech-agent-harness\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"cuonztech-agent-harness\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on your machine.
- Floor 36, ceiling 60 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/cuonztech-agent-harness
- Install plan: https://forgeregistry.com/api/v1/packages/cuonztech-agent-harness/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/cuonztech-agent-harness
- HTML page: https://forgeregistry.com/registry/cuonztech-agent-harness
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.