Skip to content
Agentmart
Submit a tool

Agent Harness

MCP chaos-testing toolkit.

Connector by cuonztech · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/cuonztech-agent-harness

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
3 read · 2 write · 2 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

  • get_report
  • get_score
  • list_scenarios

Write 2 · Create, change, send or run things.

  • execute_call
  • start_session

Delete 2 · Delete, drop, revoke or wipe things.

  • delete_session
  • reset_session

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • delete_sessionDelete Session

    Permanently deletes a session and its state.

  • execute_callExecute Tracked 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, and records the result for audit. Reads return a generic ok without data.

  • get_reportGet Audit Report

    Generates the audit report for a session. Returns markdown (chat-friendly) or JSON. Also persists JSON to .cuonztech/audit-report.json.

  • get_scoreGet Resilience 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 hardening patches for whatever violations the session actually produced. Returns n/a instead of a score when nothing was tested. Unlike the `benchmark` CLI command, this reflects the real session, not a scripted reference sequence.

  • list_scenariosList Available Scenarios

    Returns all available deterministic failure scenarios (F1–F5) with descriptions and audit metrics.

  • reset_sessionReset Session

    Resets a session's call counter and history without deleting it. Useful for re-running the same scenario.

  • start_sessionStart Test Session

    Creates an isolated test session with optional scenario (F1–F5) and mode (deterministic/chaos). Returns a sessionId for subsequent calls. Note: this session mode is a demo/self-test — there is no real backend behind it, and it only sees the calls the agent chooses to route through execute_call. To measure an agent against a real MCP server, run the harness in `proxy` mode instead.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 13, 2026 (16 days ago)
Last release
Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.cuonztech/agent-harness
Version
0.5.2
Auth
No auth
Packages
npm cuonztech-agent-harness
License
MIT
Repository
github.com/cuonztech/agent-harness
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Agent Harness MCP server. Agent Mart. https://agentmart.dev/connectors/cuonztech-agent-harness (last updated 2026-10-24)