Create Beta MCP_README

[Alek99]

All Submissions:

• Have you followed the guidelines stated in CONTRIBUTING.md file?
• Have you checked to ensure there aren't any other open Pull Requests for the desired changed?

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

New Feature Submission:

• Does your submission pass the tests?
• Have you linted your code locally prior to submission?

Changes To Core Features:

• Have you added an explanation of what your changes do and why you'd like us to include them?
• Have you written new tests for your core changes, as applicable?
• Have you successfully ran tests with your changes locally?

After these steps, you're ready to open a pull request.

a. Give a descriptive title to your PR.

b. Describe your changes.

c. Put `closes #XXXX` in your comment to auto-close the issue that your PR fixes (if such).

[codspeed-hq]

CodSpeed Performance Report

Merging #5395 will degrade performances by 3.15%

_{Comparing Alek99-patch-1 (abaa2df) with main (31be645)}

Summary

❌ 1 regressions
✅ 7 untouched benchmarks

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Benchmarks breakdown

	Benchmark	BASE	HEAD	Change
❌	test_compile_stateful[_complicated_page]	755.5 µs	780.1 µs	-3.15%

[mtln]

Great, I'll test it. Small fix for the README:

Create .vscode/mcp.json in your project:

Cursor doesn't pick up the config there. It expects the config to be in .cursor/mcp.json instead

https://docs.cursor.com/context/model-context-protocol#configuration-locations

[mtln]

Once out of alpha, this service will be integrated into Reflex Pro+ subscription plans.

Let me share my honest thought on this:
I have observed that Cursor/LLMs are really bad in writing reflex code (compared to writing FastAPI / JINJA code for example). There are two main issues I see:
1)
Reflex is not all "pure python". Syntactically yes, but semantically, one has to distinguish between code blocks in states where basic language constructs like if-else or loops don't work, but one has to do rx.cond, ~ instead of not, rx.foreach and so on.
This is often messed up in AI-assisted code.
2)
Reflex is not (yet) very stable. Annotations and other elements get deprecated. Things you had to do this way should now be done that way. This is very confusing to LLMs that learned from examples that were written for different reflex versions and they start to generate deprecated or invalid code.

So this can all be very frustrating for newbies. If someone is evaluating new frameworks to use in future projects and the first experience is not smooth and promising, he goes on to the next framework.

This is why, in my opinion, it would be a strategic mistake to make this a "Pro" feature if you want to grow.

[Alek99]

Once out of alpha, this service will be integrated into Reflex Pro+ subscription plans.

Let me share my honest thought on this: I have observed that Cursor/LLMs are really bad in writing reflex code (compared to writing FastAPI / JINJA code for example). There are two main issues I see: 1) Reflex is not all "pure python". Syntactically yes, but semantically, one has to distinguish between code blocks in states where basic language constructs like if-else or loops don't work, but one has to do rx.cond, ~ instead of not, rx.foreach and so on. This is often messed up in AI-assisted code. 2) Reflex is not (yet) very stable. Annotations and other elements get deprecated. Things you had to do this way should now be done that way. This is very confusing to LLMs that learned from examples that were written for different reflex versions and they start to generate deprecated or invalid code.

So this can all be very frustrating for newbies. If someone is evaluating new frameworks to use in future projects and the first experience is not smooth and promising, he goes on to the next framework.

This is why, in my opinion, it would be a strategic mistake to make this a "Pro" feature if you want to grow.

Fair enough we'll consider this - do you have any feedback on functionality or improvements you want

[greptile-apps]

PR Summary

Added MCP_README documenting the Model Context Protocol (MCP) Server for Reflex, which provides programmatic access to framework documentation and component information.

• New MCP Server documentation details endpoints and tools for accessing Reflex framework information
• Includes client configuration examples for different platforms
• Outlines future pricing plans and service tiers
• Documentation structure needs consistency improvements in configuration examples
• Missing version requirements and security considerations need to be addressed

_{1 file reviewed, no comments
Edit PR Review Bot Settings | Greptile}

[picklelo]

🚀