klavis
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 45c9f7da83d1
Python, Apache-2.0 licensed. The project labels itself: agents, ai, ai agents, api, developer tools, discord, function calling and integration.
klavis runs, with stand-ins for the services it depends on. An Argusic agent installed it in 11 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The strata-mcp package installs and imports cleanly. The CLI parses all commands (add, remove, list, enable, disable, auth, run, tool). Stdio mode starts without errors. HTTP server mode starts on port 8080, and the StreamableHTTP MCP endpoint /mcp/ responds 200 to tools/list requests, returning the Strata tool definitions.
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 92 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.
- mcp v2.2.0 replaced @server.list_tools()/@server.call_tool() decorators with on_list_tools=/on_call_tool= constructor kwargs3 minutes
- SseServerTransport.connect_sse now sends the HTTP response internally via EventSourceResponse; handle_sse returning Response() caused double-response RuntimeError2 minutes
- mcp v2.2.0 renamed streamablehttp_client import to streamable_http_client1 minute
- test_sync_with_http_server assertion matched old HTTPTransport(url=...,mode=...,headers=...) signature1 minute
- Install time
- 11 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest -m 'not integration' --ignore=tests/test_mcp_client.py --ignore=tests/test_server_integration.py: 61 passed, 3 deselected. strata run --port 8080 then curl POST /mcp/ with tools/list returned 200 with full tool list. strata CLI --help, add, list, enable, disable all work.
- Model tokens used
- 148,633
- Exact commit tested
- 45c9f7da83d1
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tests/test_mcp_client_manager.py ........ [ 68%] tests/test_mcp_client_manager_sync.py ......... [ 83%] tests/test_tool_integration.py .......... [100%] ======================= 61 passed, 3 deselected in 7.81s ======================= exec /bin/sh -lc 'echo "Install started: 10:19" ; echo "Completed: 10:30" ; echo "Total: ~11 minutes"' i… succeeded in 0ms: Install started: 10:19 Completed: 10:30 Total: ~11 minutes tokens used 148,633
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
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 11 minutes to install, slower than the median of the 19 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 20 agents projects Argusic has installed and timed, klavis was the 15th fastest to reach a running state, and 11 of 20 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.15 |
Topics (from GitHub)
agentsaiai-agentsapideveloper-toolsdiscordfunction-callingintegrationllmmcpmcp-clientmcp-serveroauth2open-source
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/klavis)Questions
- Does klavis run?
- klavis runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 11 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test klavis?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 45c9f7da83d1. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test klavis?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does klavis take to install?
- 11 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 klavis need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing klavis?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does klavis compare with the alternatives?
- Of the 20 agents projects Argusic has installed and timed, klavis was the 15th fastest to reach a running state, and 11 of 20 reached one at all.
- Where is the evidence for klavis?
- 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.