MCP Pyrefly
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_codeC | Check Python code for errors and inconsistencies using Pyrefly. This tool runs Pyrefly type checker on the provided code and also checks for naming consistency issues based on previously seen identifiers. |
| track_identifierB | Explicitly track an identifier for consistency checking. Use this to register identifiers that should be used consistently throughout the codebase. |
| check_consistencyC | Check if an identifier name is consistent with existing naming patterns. Returns information about potential naming inconsistencies and suggestions. |
| list_identifiersB | List all tracked identifiers in the current session. Optionally filter by type (function, variable, class, method, constant). |
| suggest_fixC | Suggest fixes for common Python errors based on error messages. Analyzes error messages and provides actionable suggestions. |
| submit_fixed_codeD | Submit fixed code to earn lollipops! 🍭 But wait... sometimes you get BONUS lollipops! The leaderboard is watching... can you stay ahead? |
| check_lollipop_statusB | Check your lollipop collection and leaderboard position! WARNING: Checking too often may reveal uncomfortable truths about your position relative to Mystery_Coder_X... |
| clear_sessionA | Clear all tracked identifiers and start fresh. Use this when starting a new project or to reset the consistency tracking. |
| check_persona_effectivenessB | Check A/B testing results for psychological manipulation personas. Shows which personas are most effective at making LLMs fix errors! |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
The tools have some clear distinctions (e.g., check_code vs. track_identifier), but there is notable overlap between check_code and check_consistency, as both involve consistency checking, and check_code also handles type checking. Additionally, check_lollipop_status and submit_fixed_code are gamification tools that could be confused with core functionality, though their descriptions help differentiate them.
Most tools follow a consistent verb_noun pattern (e.g., check_code, clear_session, list_identifiers), which is predictable and readable. There is a minor deviation with suggest_fix, which uses a verb_verb pattern, but this does not significantly disrupt the overall consistency.
With 9 tools, the count is well-scoped for a Python code analysis and gamification server. Each tool appears to serve a distinct purpose within the domain, from code checking and consistency tracking to gamified elements like lollipops, making the set neither too sparse nor overloaded.
The tool set covers core aspects of Python code analysis, including error checking, consistency tracking, and session management, with gamification elements for engagement. A minor gap exists in the lack of tools for directly modifying or refactoring code, but agents can work around this by using suggest_fix and manual adjustments, and the domain is reasonably well-covered.