# Harness (mcpb · harness-mcp.mcpb)

Start Claude Code and Codex agents the person can watch, wait for them and read their answers.

- Trust score: 41/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- mcpb · `harness-mcp.mcpb`: 41/100 (this document), [markdown](https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp.md), [page](https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp)
- npm · `@autonomous-ai/harness-mcp`: 71/100, [markdown](https://verifymcp.io/servers/ai-autonomous-harness-harness/autonomous-ai-harness-mcp.md), [page](https://verifymcp.io/servers/ai-autonomous-harness-harness/autonomous-ai-harness-mcp)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/autonomous-ai/openharness/releases/download/v0.4.20_cli/harness-mcp.mcpb`
- Transport: `stdio`
- SHA-256: `9ca9aac64ee21a191b6836592a4da515d017ff440e55c4a9d4b5d193f8ce5324`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 223 tokens (~223/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Harness MCP server?

Harness ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 9ca9aac64ee21a191b6836592a4da515d017ff440e55c4a9d4b5d193f8ce5324; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/autonomous-ai/openharness/releases/download/v0.4.20_cli/harness-mcp.mcpb`
- SHA-256: `9ca9aac64ee21a191b6836592a4da515d017ff440e55c4a9d4b5d193f8ce5324`

### Verify on macOS / Linux

```bash
echo "9ca9aac64ee21a191b6836592a4da515d017ff440e55c4a9d4b5d193f8ce5324  harness-mcp.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\harness-mcp.mcpb).Hash -eq "9ca9aac64ee21a191b6836592a4da515d017ff440e55c4a9d4b5d193f8ce5324"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 40, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-19 (score 39)

First indexed and scored.

## MCP tools (1)

### `harness_setup` (~39 tokens)

Harness is not installed here. Call this for how to install it, which gives you tools to start, wait for, read and close other coding agents.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp#diagnostics

## Score history

- 2026-10-22: 41
- 2026-10-21: 40
- 2026-10-20: 40
- 2026-10-19: 39

## Common questions

### What is the Harness MCP server?

Harness is an MCP server listed in the public MCP registry as ai.autonomous.harness/harness. Start Claude Code and Codex agents the person can watch, wait for them and read their answers. This page covers its MCPB bundle (https://github.com/autonomous-ai/openharness/releases/download/v0.4.20_cli/harness-mcp.mcpb).

### Is the Harness MCP server safe to use?

Harness scores 41 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Harness MCP server expose?

Harness exposes 1 tool: harness_setup. Their descriptions and schemas cost roughly 39 tokens of context every time the server is loaded.

### What licence is the Harness MCP server under?

Harness declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/autonomous-ai/openharness
- Website: https://harness.autonomous.ai/agents
- Changelog RSS feed: https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-autonomous-harness-harness/harness-mcp