toolhive
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
Runssource: GitHubhomepageGoApache-2.0commit 88bb28433ae7
Go, Apache-2.0 licensed. The project labels itself: ai, ai security, aicodeassistant, golang, kubernetes, mcp, mcp security and mcp servers.
toolhive runs. An Argusic agent installed it in 55 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
ToolHive v0.51.3 builds from source with the standalone Go 1.27.1 compiler. The thv binary starts, prints its help page, and outputs version/build information. Unit tests pass at 198/201 with the 3 failures all due to missing Docker or system keyring in this container.
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 88 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 compiler (golang) not found in container — no go binary in PATH5 minutes
- Task runner (go-task) not installable — dependency name mismatch in go-task's go.mod5 minutes
- API tests fail — require Docker container runtime (pkg/api)
- bodylimit test hangs indefinitely (pkg/bodylimit)
- Keyring test fails — no system keyring provider available (pkg/secrets/keyring)
- Install time
- 55 minutes
- Cold machine to finish
- 55 minutes
- Errors hit and fixed
- 5 hit, 2 fixed with no human help
- How the result was proved
- go test -race run on all 201 pkg/ and cmd/ test targets (excluding mocks, e2e, integration): 198 PASS, 3 FAIL. Binary ./bin/thv version exits 0 and prints version info; ./bin/thv (no args) prints full command help.
- Model tokens used
- 192,012
- Exact commit tested
- 88bb28433ae7
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
-rwxrwxr-x 1 runner runner 128M Oct 4 02:36 /work/repo/bin/thv exec /bin/sh -lc 'cd /work/repo && export PATH="/home/runner/go/bin:$HOME/go/bin:$PATH" && ./bin/thv ver… succeeded in 0ms: You are running a local build of ToolHive Exit: 0 Here's the final summary. The main binary (`thv`) builds and runs — `thv version` exits 0 and prints version info, and `thv` … tokens used 192,012 Here's the final summary. The main binary (`thv`) builds and runs — `thv version` exits 0 and prints version info, and `thv` …
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.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 55 minutes to install, slower than the median of the 82 comparable projects Argusic has measured.
- Hit 5 errors during setup, 3 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 83 ai projects Argusic has installed and timed, toolhive was the 82nd fastest to reach a running state, and 58 of 83 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)
aiai-securityaicodeassistantgolangkubernetesmcpmcp-securitymcp-serversmcp-toolsmodel-context-protocolsecurity
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/toolhive)Questions
- Does toolhive run?
- Yes. toolhive runs. Argusic installed and launched it on a clean machine in 55 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test toolhive?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 88bb28433ae7. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test toolhive?
- The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does toolhive take to install?
- 55 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 toolhive need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing toolhive?
- 5 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does toolhive compare with the alternatives?
- Of the 83 ai projects Argusic has installed and timed, toolhive was the 82nd fastest to reach a running state, and 58 of 83 reached one at all.
- Where is the evidence for toolhive?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.