mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
Runs with mockssource: GitHubPythonApache-2.0commit f62d84935081
Python, Apache-2.0 licensed. The project labels itself: agents, ai, ai agents, llm, llms, mcp, model context protocol and python.
mcp-agent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
mcp-agent 0.2.6 installs, builds, CLI boots, and all 1501 tests pass after fixing the abstract generate_stream method in the base AugmentedLLM class and patching the Bedrock streaming test mock.
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.
- Base class AugmentedLLM declared generate_stream as @abstractmethod but subclasses OpenAIAugmentedLLM, AzureAugmentedLLM, GoogleAugmentedLLM, Orchestrator, DeepOrchestrator, ParallelLLM, EvaluatorOptimizerLLM, Swarm, LMStudioAugmentedLLM, OllamaAugmentedLLM did not implement it, causing TypeError on instantiation8 minutes
- Bedrock streaming test expected usage tokens (input_tokens=100, output_tokens=50) but mock events did not include a metadata event with usage data, causing assertion failure2 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 20 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 224,234
- Exact commit tested
- f62d84935081
- Container image
- sha256:4c3d41857be3
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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
- **errors**: 2 errors found and fixed: 1. `@abstractmethod` on `generate_stream` preventing instantiation of many LLM classes 2. Missing metadata event in Bedrock streaming test mock tokens used 224,234 Now let me compile the results: - **install_succeeded**: Dependencies installed via `uv sync`, project builds and imports correctly - **launch_succeeded**: Full test suite (1501 tests) passes, CLI starts and shows help - **test_depth**: `tier2_mock` - all tests pass but they use mocks (no real LLM API keys configured… - **errors**: 2 errors found and fixed: 1. `@abstractmethod` on `generate_stream` preventing instantiation of many LLM classes 2. Missing metadata event in Bedrock streaming test mock
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 2 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 4.5 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 8 agents projects Argusic has installed and timed, mcp-agent was the 6th fastest to reach a running state, and 5 of 8 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 | 2/3 | Runs with mocks | 92.00 | 0.07 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-agent)Questions
- Does mcp-agent run?
- mcp-agent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test mcp-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f62d84935081. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp-agent?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-agent take to install?
- 4.5 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 mcp-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-agent?
- 2 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 mcp-agent compare with the alternatives?
- Of the 8 agents projects Argusic has installed and timed, mcp-agent was the 6th fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for mcp-agent?
- 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.