agentdock
Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.
Runssource: GitHubhomepageGoApache-2.0commit 81ef14e7dec2
Go, Apache-2.0 licensed. The project labels itself: agent skills, ai agents, automation, devops, docker, mcp, model context protocol and remote control.
agentdock runs. An Argusic agent installed it in 12 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
AgentDock v0.9.1 builds, starts, serves its web UI on HTTP, answers MCP JSON-RPC with 18 tools, and passes all 52 test packages including with race detection, all in the container without modifying any repository files.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Go 1.26.5 was not installed in the container3 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- go test ./... exited 0 on all 52 packages; go test -race ./... exited 0 on all 52 packages; agentdock binary printed version AgentDock v0.9.1; MCP POST to /mcp with tools/list returned 18 tools; server web UI returned HTTP 200 on GET /
- Model tokens used
- 43,808
- Exact commit tested
- 81ef14e7dec2
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 43,808 Everything passes cleanly. Now let me produce the final report. **Summary of what happened:** - The project is **AgentDock MCP** (`github.com/uvwt/agentdock`), a Go project requiring Go 1.26.5 - Go was not pre-installed; a bundled Go 1.26.5 tarball was extracted to `/tmp/go` - `go build ./cmd/agentdock` succeeded, producing `bin/agentdock` (28 MB binary) - `agentdock --version` printed `AgentDock v0.9.1` with the correct build info - `agentdock` server started and served its web UI on HTTP (200 on `/`) and answered MCP JSON-RPC o… - `go test ./...` — all 52 testable packages passed (0 failures, 0 errors) - `go test -race ./...` — all packages passed the race detector as well - No third-party API keys required for basic verification; auth is optional
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.
Of the 128 agent-skills projects Argusic has installed and timed, agentdock was the 110th fastest to reach a running state, and 96 of 128 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsai-agentsautomationdevopsdockermcpmodel-context-protocolremote-controlself-hostedtool-calling
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agentdock)Questions
- Does agentdock run?
- Yes. agentdock runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test agentdock?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 81ef14e7dec2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test agentdock?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agentdock take to install?
- 12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agentdock need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agentdock?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agentdock compare with the alternatives?
- Of the 128 agent-skills projects Argusic has installed and timed, agentdock was the 110th fastest to reach a running state, and 96 of 128 reached one at all.
- Where is the evidence for agentdock?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.