Progressor
Your AI's plan, saved in your project and shown live on a dashboard.
Progressor is an MCP server for AI coding apps (Claude Code, Claude Desktop, Cursor, VS Code with Copilot, Windsurf, Codex and others). Your AI writes its plan into your project as a goal made of steps, and ticks each step off as it works. You watch every project on one page in your browser. Because the plan lives in your project, not in the chat, your AI picks up from the exact step it was on after its memory is compressed, or when you switch to another AI app.
This is the Python package of Progressor. It is the same Progressor as the npm package, and it brings its own Node.js, so you don't need Node installed.
Set it up
With uv, in your project's folder:
uvx progressor-mcp init
That one command sets up Claude Code and Claude Desktop: the server, the hooks that hand your AI the plan at the start of every conversation, and a short note telling it to use Progressor. Restart your AI app, then ask it to plan something.
For other apps, add this server to the app's MCP settings (where each app keeps them):
{
"mcpServers": {
"progressor": { "command": "uvx", "args": ["progressor-mcp"] }
}
}
then run uvx progressor-mcp init --no-server in your project's folder.
Prefer pip? pip install progressor-mcp (or uv tool install progressor-mcp) gives you the progressor-mcp command; use it in place of uvx progressor-mcp above.
The dashboard
It opens at http://localhost:4747 while your AI app is running, and shows every project at once. To keep it up all the time: progressor-mcp daemon install.
Update it
- uvx:
uv cache clean progressor-mcp, then restart your AI app. - uv tool:
uv tool upgrade progressor-mcp. - pip:
pip install -U progressor-mcp.
The dashboard tells you when a newer version is out, with the command for your setup.
More
The full guide, screenshots and a 5-minute video are on GitHub.
Free for personal use. Using it in a business, or selling, hosting or building a product on it, needs a license from the author: ask for one. See LICENSE.md.
Metadata
Release files for progressor-mcp 1.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| progressor_mcp-1.4.0.tar.gz | 4.1 MB | Without provenance | Details for progressor_mcp-1.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| progressor_mcp-1.4.0-py3-none-any.whl | Python 3 | none | any | Details for progressor_mcp-1.4.0-py3-none-any.whl |
Total release size: 10.2 MB
Release files / progressor_mcp-1.4.0.tar.gz
| Download URL | progressor_mcp-1.4.0.tar.gz |
|---|---|
| Size | 4.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c77571af9381432dea3a29656bc184441073b626c203e9de1ca2b2dfc5705faf
|
|
BLAKE2b-256 checksum How to use checksums |
ff163786794d48c1d9ceb1ecb6693e48b353315d77c5bac527ca3a4179287bbb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
Release files / progressor_mcp-1.4.0-py3-none-any.whl
| Download URL | progressor_mcp-1.4.0-py3-none-any.whl |
|---|---|
| Size | 6.1 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
72b675895811d2b958bd221d0e6bdcf11521402f0f5c66d5b0e1d6109c21b81c
|
|
BLAKE2b-256 checksum How to use checksums |
008a77becf45ba477bdc0bdb10e1867907562757c4e52e29283a9a6e8fa12fce
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
Security for progressor-mcp 1.4.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.