moongioh-harness-scopeCAUTION
Turn-level governance observability for Claude Code — parse your transcripts locally, judge them against your own workspace rules, see where tokens die. No LLM inside; nothing leaves your machine.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/hscope/) [](https://www.npmjs.com/package/hscope) [](https://github.com/moongioh/harness-scope/actions/workflows/harnesses.yml) [](LICENSE) [](#)
Turn-level governance observability for agent harnesses. HarnessScope reads the transcripts your agent harness already writes, judges every turn against your workspace's own operating rules (plan-before-code, verify-before-done, context budget, path boundaries, ...), and serves a local viewer that shows how each session traversed that governance structure — passes included, not just violations.
Every frame above is `hscope demo`: a synthetic corpus, generated locally. Real transcripts carry full prompt text and are never demo material.
What it found
A session is not one model talking to itself — it spawns subagents, they run on models the parent does not, and a streamed response writes the same request several times. Read that structure naively and the numbers are wrong. These are the corrections, each measured on this project's own transcripts:
101cb1f33027OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add hscope -- npx -y [email protected] mcp
claude mcp add hscope -- uvx hscope==0.1.4 mcp
Trust audit
CAUTIONgrade B · trust 88/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
print(f"\nserving the demo on http://127.0.0.1:{port}")f"serve http://127.0.0.1:{port}",proxy: { "/api": "http://127.0.0.1:8000" },FROM python:3.12-slim
# → http://127.0.0.1:8000
PyYAML, fastapi, uvicorn
react, react-dom, @types/react, @types/react-dom, @vitejs/plugin-react, typescript, vite
Gates applied: no_behavioural_pass.
101cb1f33027full audit observations/trust-audit/mcp-server/moongioh__harness-scope.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 101cb1f33027 | CAUTION | B | 88 | first audit |
Questions
What is the moongioh-harness-scope MCP server?
Turn-level governance observability for Claude Code — parse your transcripts locally, judge them against your own workspace rules, see where tokens die. No LLM inside; nothing leaves your machine.
Is moongioh-harness-scope safe to connect to an agent?
With care. The audit graded it B (88/100) and found 8 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does moongioh-harness-scope need?
It reads HSCOPE_EDIT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does moongioh-harness-scope run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as harness-scope-web at 0.3.0.
How current is this page?
The grade is for one exact copy of the source (101cb1f33027), read on 2026-10-12. The repository is watched and re-audited when it changes.