Harness MCP server
ai.autonomous.harness/harness·v0.4.20·1.4k starsStart Claude Code and Codex agents the person can watch, wait for them and read their answers.
1.4k stars161 downloads/wk
Reviews
Write oneNobody has reviewed Harness yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Harness tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
harness_setupHarness 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.
Public scan report
scanner v0.1.10 · 2026-10-27 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10
How Harness compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 48,273 servers
- Tools
- 1
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1,375
- more than 95% of 28,534 servers
- Downloads a week
- 161
- more than 72% of 11,915 servers with a package
What its tools let an agent do: 1 read
Install Harness in Claude Code, Cursor or VS Code
Runs npx -y @autonomous-ai/harness-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add harness -- npx -y @autonomous-ai/harness-mcp
What the publisher says
From the Harness repository's README, as published. We do not edit it. Read it on GitHub
Harness like a boss.
The ultimate harness for coding agents and beyond. Claude Code at work. Codex at home. Hermes in the cloud. One command center. Start with code. Then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
Download · How it works · Beyond code · Harnesses · Device
Every agent, side by side
Claude Code, Codex, Cursor, OpenCode, Devin, Amp, Copilot and seven more.
Every machine, side by side
Your laptop, home server and GPU box in one window. Link each one with a password. No SSH keys. No Tailscale. No port forwarding.
Keyboard first
⌘P finds any harness on any machine. ⇧⌘I jumps to the harness waiting on you. ⌘D splits. Every key remaps.
End-to-end encrypted
Code, keys and keystrokes are sealed on your machine. The relay forwards bytes it can't read.
Fast and light
A native app, not Electron. Close it and your agents keep working.
Idle measurements on an M2 Max:
- ⌘N, ⌘O, ⌘T UI: 11–13 ms median, 15–18 ms p95.
- Local terminal echo: 1.1 ms median, 7.2 ms p95, excluding UI rendering.
- Desktop resources: ~0.1% of one CPU core and 304 MiB, including terminal rendering and scrollback; agent CLIs and the daemon are excluded.
Desktop results use a Release fixture with 16 terminals and 1,000 scrollback lines each. See the workflow and resource benchmarks and remote P2P, TURN and relay results for workloads, slow tails, connection failures and raw data.
Built the way developers work
- Real terminals. Every agent runs in its own tmux pane. Scrollback, colors and keys just work.
- Your CLIs, as they are. Harness never wraps an agent. It reads transcripts and uses the vendor's own hooks.
- A worktree per harness. Start an agent on its own branch. Your working copy stays clean.
- Remap every key. One JSONC file, reloaded on save. Chords up to four strokes.
- Local models. Run open-weight models on your own machines with Grid, Ollama, MLX-LM and vLLM.
- Bytes, not pixels. Remote terminals stream text peer to peer. No remote desktop.
- Open source, all of it. App, CLI, daemon, relay and device, in this repo.
How it works
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Harness: common questions
- Is Harness MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Harness safety report
- How do I install Harness?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Harness need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Harness maintained?
- The last commit was 6 days ago (2026-10-27). The latest release is v0.4.20.
- How does Harness compare with other MCP servers?
- safety score 92/100 (higher than 90% of 48,273 servers); tools 1 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.