Provides a local practice environment for AI agents to perform tasks on real applications like Excalidraw and receive reproducible performance scores.
Also known as godarg/practonaut
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.0
- Last commit
- Nov 10, 2026
- License
- Apache-2.0
What is Practonaut MCP?
Practonaut provides a local practice environment for AI agents to perform tasks on real applications like Excalidraw and receive reproducible performance scores.
Summary generated from the project's README
About Practonaut MCP server
Practonaut provides a local practice environment designed for AI agents to train on real applications. Currently, it supports Excalidraw, allowing agents to perform specific tasks like connecting steps or recoloring elements. Instead of simulating a GUI through pixel clicking, agents interact via semantic actions through an MCP client. This setup ensures that every action is applied to a real, pinned Excalidraw engine running in a headless Chromium shell, which is installed via a setup command.
Developers use this tool to benchmark agent performance using reproducible scores. By running the bench command, you can evaluate agents against reference solutions to calculate metrics such as pass@1 and efficiency. The system uses a separate checker to decide if a goal is met, ensuring the results are independent of the agent's own claims. It is a local-first tool that requires Node.js and does not require a VM or Docker, making it easy to integrate into existing development workflows or CI pipelines.
What you can do with it
- 1Monitor agent progress visuallyWatch an agent work on a task in real-time through a browser-based player.
- 2Detect performance regressionsCompare two different benchmark reports to see if recent changes negatively impacted agent capabilities.
Written from the project's README. Every use case is checked against a quote from it.
How to install Practonaut MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Practonaut MCP in Claude Code
$ claude mcp add practonaut -- npx -y practonautInstall Practonaut MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"practonaut": {
"command": "npx",
"args": [
"-y",
"practonaut"
]
}
}
}Install Practonaut MCP in VS Code
.vscode/mcp.json
{
"servers": {
"practonaut": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"practonaut"
]
}
}
}Install Practonaut MCP in VS Code CLI
$ code --add-mcp '{"name":"practonaut","type":"stdio","command":"npx","args":["-y","practonaut"]}'Install Practonaut MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"practonaut": {
"command": "npx",
"args": [
"-y",
"practonaut"
]
}
}
}Install Practonaut MCP in Codex
$ codex mcp add practonaut -- npx -y practonautInstall Practonaut MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.practonaut] command = "npx" args = ["-y", "practonaut"]
Install Practonaut MCP in Gemini CLI
$ gemini mcp add -s user practonaut npx -- -y practonautInstall Practonaut MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"practonaut": {
"command": "npx",
"args": [
"-y",
"practonaut"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablegodarg/practonaut is public and reachablegithub.com/godarg/practonaut ↗Pass
- Package names this repository as its sourcepractonaut names godarg/practonaut as sourcenpmjs.com/package/practonaut ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for practonautnpmjs.com/package/practonaut/v/0.2.0#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/godarg/practonaut ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from practonautPass
- No critical advisory in the package or its dependencies7 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubPractonaut
A local practice gym for AI agents on real apps. Demonstrate a task once, let any MCP agent
practise it, and get an independent, reproducible score — one npx command, no VM, no Docker.
Practonaut turns a real application — today Excalidraw — into a practice environment. A task is a start drawing plus a goal. You, or an agent over MCP, change the diagram one action at a time; each action is applied to a real, pinned Excalidraw engine and read back before it counts. When the attempt ends, a separate checker decides whether the goal is met. People and agents work on the same session at the same time, so you can watch an agent in your browser: the history marks each change as yours or as the agent's (Agent · claude-code).
Quick start in 60 seconds
Requires Node.js 22.18 or newer (macOS, Linux or Windows).
npx practonaut # opens the example task in your browser at once
npx practonaut setup # once: the Chromium headless shell for the real Excalidraw engine (about 105–130 MB)
Watch a demonstration in the Player solves the example task once: actions land on the board,
the real Excalidraw confirms each one, and the result check judges the end. It is never your
result; Stop or Escape ends it. Before setup everything works model-only: actions are not
confirmed in the real app, and a banner says so and names the download.
Let an agent practise (Claude Code shown; any MCP client works):
claude mcp add practonaut -- npx -y practonaut mcp --task excalidraw/connect
On native Windows (not WSL) npx is a .cmd file that an MCP client cannot start directly; add
cmd /c in front: claude mcp add practonaut -- cmd /c npx -y practonaut mcp --task excalidraw/connect.
Score it on a task, with a fresh session per run and an independent check:
npx practonaut bench --agent claude-code --tasks excalidraw/connect
More in getting started.
Create your own task
Draw the start and the goal in Excalidraw, then:
npx practonaut tasks from-scenes start.excalidraw goal.excalidraw --out my-task
npx practonaut play my-task/world
The difference becomes the goal (steps, labels, shapes, colours, frames, groups, arrows). Practonaut only writes the task if the goal passes its own check, the start fails, a generated reference solution passes and generated near misses fail. The same works in the Player under Create, where you can also record a demonstration in the real editor and have the rule confirmed by a second recording. See the authoring guide.
Benchmark your agent
npx practonaut bench --agent oracle --tasks all --seeds 2 # reference solutions: the score's ceiling
npx practonaut bench --agent random --tasks all --max-actions 30 # random actions: the floor
npx practonaut bench --agent claude-code --tasks excalidraw/insert-between --repeats 3
npx practonaut bench --agent "my-agent --mcp {mcp_config} --prompt {prompt}" # any agent
npx practonaut bench --agent claude-code --world my-task/world --oracle my-task/oracle.json # your own task
npx practonaut report ~/.practonaut/bench/<id>/report.json --html report.html
npx practonaut report ~/.practonaut/bench/<id>/report.json --verify # re-judge from the run files
npx practonaut compare before/report.json after/report.json --fail-on-regression # did a change break an instance?
npx practonaut report ~/.practonaut/bench/<id>/report.json --junit runs.xml --card card --badge badge.svg
Each run gets its own session and data folder; the agent reaches the session only through the
Practonaut MCP tools and gets the same public task a person gets. The claude-code preset does not
pass provider keys, tokens or billing switches from your environment to Claude Code (a set
ANTHROPIC_API_KEY would silently switch it to API billing), so Claude Code uses the login it has —
your subscription, if you logged in with one; --keep-env ANTHROPIC_API_KEY passes a key on
purpose. Scores come from the host's history and a
separate checker, never from what the agent says: pass@1, pass^k, actions, efficiency against the
reference solution. The JSON report has a schema. report checks that every pass and every number
follows from the verdicts in the file — consistency, not proof: a file edited consistently still
passes, and report says "consistency-checked, not re-verified". report --verify re-runs the
checker on the session and the real-app export kept in the bench folder, whose SHA-256 the report
records, against the world and reference solutions stored in that folder (so a moved folder still
verifies), re-derives each run's actions and reference length, and refuses any difference by name; host calls and times are marked as reported by the runner. Nothing is
signed: whoever can write the bench folder can replace those files too.
A report says why a run failed, not only that it did: rates as fractions with a 95 % interval, failed
runs first, each unmet goal condition with the action after which it was last lost (judged by the
checker after every action), error classes with their explanation, the trajectory, the final board —
the real Excalidraw's own export, or a schematic labelled as such — beside an example target, the
call log and the tokens, turns and cost the client reports about itself. compare puts two reports
side by side instance by instance: it refuses reports that are not comparable, names instance
regressions (three repeats a side, all passed before, all failed after) and says "not
distinguishable at this n" when an exact McNemar test cannot tell the two apart. Both reports must come
from the same kind of agent: oracle and random mark the ends of the score and compare only with a
built-in, a command template only with a command template; as the baseline for your agent, bench a
configuration of it that you trust.
In CI, examples/ci/practonaut-bench.yml benches your agent with
your own credentials and fails the job on an instance regression against a committed baseline; --junit
gives CI test views one test case per run. --card and --badge draw the header line as a 1280 × 640
card (SVG and PNG, light and dark) and a badge, with n, the interval, the verification status and the
isolation level on them.
The example report is a real run of Claude Code on three tasks, two repeats each (JSON, HTML) — one seed, six runs: it shows the format, it does not rank a model. Details: benchmarks.
Task library
Library, not a challenge tier. These tasks are an example set and a shared smoke test, not a measure of ability: current Claude models solve them, and five harder candidate families found no headroom on Practonaut's own actions in 0.2.0 (gate reports). A family becomes a challenge tier only after it passes a preregistered ladder gate.
16 tasks for Excalidraw 0.18.1, each in English and German with three label variants, a reference
solution and near misses. List them with npx practonaut tasks list; open one with
npx practonaut play <task>; address them as excalidraw/<task> in mcp and bench.
| Task | Level | Reference actions | Goal |
|---|---|---|---|
add-step |
●○○ | 1 | Add a step |
connect |
●○○ | 1 | Connect two steps |
disconnect |
●○○ | 1 | Remove a shortcut arrow |
recolor |
●○○ | 1 | Mark the error step |
remove-step |
●○○ | 1 | Remove a step |
rename-frame |
●○○ | 1 | Name the frame |
rename-step |
●○○ | 1 | Fix a label |
align |
●●○ | 3 | Align a row |
close-chain |
●●○ | 1 | Close the gap in a chain |
group |
●●○ | 2 | Group a sub-process |
insert-between |
●●○ | 4 | Insert a step between two others |
reconnect |
●●○ | 1 | Rewire an arrow |
reorder |
●●○ | 4 | Put the steps in order |
decision |
●●● | 6 | Build a decision with two exits |
restyle-flow |
●●● | 6 | Turn a list into a styled flow |
two-frames |
●●● | 4 | Sort two sub-processes into frames |
How scoring works
- The host keeps the history. Every action goes through one session host. It records each action with a state hash and who made it; agents and people cannot write the state any other way.
- The real engine confirms each action. With Chromium installed, each action is applied to a pinned Excalidraw running headless and read back; an action the real app disagrees with is rejected.
- A separate checker decides. After the attempt, another process replays the history with its own interpreter, reads the real Excalidraw export with its own parser, and evaluates the goal. It first makes sure an empty, an unchanged and a wrong submission all fail.
An agent gets the same task and the same public goal conditions as a person in the Player — one sentence per condition plus its formal form, which is the goal predicate written out — and the same Check button. It acts through Practonaut's semantic actions over MCP, not through the GUI. The reference solution, the near misses and held-out checker data never reach it over MCP.
Limits
- One application. Excalidraw 0.18.1 is the only app so far. The adapter contract is meant for more (adapter guide); none exists yet.
- Semantic actions, not pixels. Agents act through Practonaut's actions (add a step, connect, rename, …), not by clicking a screen. This measures whether an agent can reach a goal in the app's model, not whether it can operate the GUI.
- Not sealed. Agents run as your OS user. An agent with its own file or shell tools could read
the task library on disk, reference solutions included. The
claude-codepreset allows only Practonaut's tools; for other agents that is up to you. - Small evidence so far. The example report has two runs per task. Whether practising here makes people better at the real tool has not been studied.
- Without Chromium Practonaut runs model-only: tasks work, but nothing is checked against the real app, and it says so.
- Screen-reader and 200 % zoom checks by a person: one run so far (VoiceOver on macOS with Chrome, 2026-10-17), no problems found; other screen readers and regular screen-reader users are not tested yet (manual checks).
Requirements
- Node.js ≥ 22.18 and npm.
- Optional:
npx practonaut setupdownloads Playwright's Chromium headless shell once for the real engine. Nothing is downloaded on install; the package has no install script. - Local data lives in
~/.practonaut(orPRACTONAUT_HOME). No telemetry, no account. Practonaut's own process makes no network calls while practising (npxfetches the package andsetupfetches Chromium, each once); an agent you connect talks to its own model provider.
Documentation
Getting started · Agent guide · Benchmarks · Authoring · World format · Architecture · Adapter guide · Session host · Threat model · Glossary · All documents
Contributing
Issues and pull requests are welcome — new tasks, bug fixes, and especially a second application adapter. Start with CONTRIBUTING.md; setup is three commands. Security reports go through SECURITY.md.
License
Apache License 2.0; see NOTICE. The bundled Excalidraw engine and fonts keep their own licenses (shipped with the package). The example world and the task library are CC0-1.0.
Practonaut MCP questions
How do I add Practonaut MCP to Claude Code?
Run claude mcp add practonaut -- npx -y practonaut in your terminal. Add --scope user to make it available in every project.
How do I add Practonaut MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How is the agent's performance scored?
Scores are derived from the session history and an independent checker that evaluates the final state against the goal, rather than relying on the agent's own claims.
Does it require a virtual machine or Docker?
No, it runs with a single npx command without needing a VM or Docker.