MCP Pyrefly Autotype Server
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_python_fileB | Analyze a Python file for missing type annotations |
| add_types_to_fileC | Add type annotations to a Python file using Pyrefly |
| type_check_fileC | Run type checking on a Python file using Pyrefly |
| get_project_contextC | Get project-wide type information for better type inference |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_typing_needs | Analyze a Python file or project to determine typing needs |
| type_improvement_plan | Create a plan for improving type coverage in a project |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Pyrefly Analysis Status | Current status and capabilities of the Pyrefly type analyzer |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: adding types, analyzing for missing types, getting project context, and type checking. There is no overlap in functionality, and an agent can easily differentiate between them based on their specific actions.
The tools follow a consistent verb_noun pattern (e.g., add_types_to_file, analyze_python_file), with all using snake_case. However, 'get_project_context' slightly deviates by using 'get' instead of a more action-oriented verb like 'analyze' or 'type', but overall the naming is predictable and readable.
With 4 tools, the server is well-scoped for its purpose of Python type annotation and checking. Each tool serves a specific role in the workflow, from analysis to application and verification, making the count appropriate and efficient.
The tool set covers core workflows for type annotation: analysis, context gathering, type addition, and type checking. A minor gap exists in not having a tool to remove or update existing type annotations, but agents can work around this, and the surface is largely complete for the stated purpose.