mcp-server-analyzer
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ruff-checkA | Lint Python code using RUFF to identify style violations and potential errors. |
| ruff-formatB | Format Python code using RUFF's fast formatter. |
| ruff-check-ciA | Run RUFF linter with CI/CD-specific output formats. |
| ty-checkB | Type-check Python code using ty. |
| vulture-scanC | Detect dead/unused code using VULTURE. |
| biome-checkA | Lint JavaScript/TypeScript code using Biome. |
| biome-formatA | Format JavaScript/TypeScript code using Biome. |
| analyze-codeA | Comprehensive analysis combining Ruff linting, ty type checking, and Vulture dead code detection. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_overview | Overview of available analyzers and tools. |
| get_analyzer_versions | Return current versions of installed analyzers. |
TDQS
Scored across 8 tools
Most tools are clearly distinct by language and action (format, lint, type-check, dead-code scan). The only real ambiguity is ruff-check vs. ruff-check-ci, which differ only in CI-specific output formatting.
Names generally follow a consistent 'tool-action' hyphenated pattern (ruff-format, biome-check, vulture-scan). analyze-code breaks the pattern slightly by leading with the action rather than the tool.
Eight tools is a reasonable size for a code-analysis server. The count is slightly padded by ruff-check-ci and the combined analyze-code, which overlap with existing tools, but the overall scope remains manageable.
Python coverage is strong: format, lint, type-check, dead-code, and a combined analysis. JavaScript/TypeScript support is thinner, with only formatting and linting and no type-checking or dead-code detection, leaving a notable gap for a general analyzer.