code-lens
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TASK_TTL_MS | No | Default task result retention in milliseconds. | 300000 |
| GEMINI_MODEL | No | Override the default Gemini model for all tools. | gemini-3-flash-preview |
| GEMINI_API_KEY | No | Gemini API key. Falls back to GOOGLE_API_KEY if not set. | |
| GOOGLE_API_KEY | No | Alternative Gemini API key. Used if GEMINI_API_KEY is not set. | |
| MAX_DIFF_CHARS | No | Maximum diff size in characters. | 120000 |
| MAX_TASK_TTL_MS | No | Upper bound for request-provided task TTL in milliseconds. | 3600000 |
| GEMINI_BATCH_MODE | No | Enable Gemini batch mode. | off |
| MAX_CONCURRENT_CALLS | No | Maximum concurrent Gemini API calls. | 10 |
| GEMINI_DIFF_CACHE_TTL_S | No | Cache TTL in seconds when caching is enabled. | 3600 |
| GEMINI_DIFF_CACHE_ENABLED | No | Enable Gemini context caching for large diffs. | false |
| MAX_CONCURRENT_BATCH_CALLS | No | Maximum concurrent batch Gemini calls. | 2 |
| GEMINI_HARM_BLOCK_THRESHOLD | No | Safety filter threshold (BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE). | BLOCK_NONE |
| MAX_CONCURRENT_CALLS_WAIT_MS | No | Wait timeout for concurrency semaphore in milliseconds. | 2000 |
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 |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_diffA | Generate a diff of the current branch working changes and cache it for all review tools. You MUST call this tool before calling any other review tool. Use "unstaged" for working-tree changes not yet staged, or "staged" for changes already added with git add. |
| analyze_pr_impactA | Assess impact and risk from cached diff. Prerequisite: generate_diff. Auto-infer repo/language. |
| generate_review_summaryA | Summarize diff and risk level. Prerequisite: generate_diff. Auto-infer repo/language. |
| generate_test_planA | Generate test cases. Prerequisite: generate_diff. Auto-infer repo/language/framework. |
| analyze_time_space_complexityA | Analyze Big-O complexity. Prerequisite: generate_diff. Auto-infer language. |
| detect_api_breaking_changesA | Detect breaking API changes. Prerequisite: generate_diff. Auto-infer language. |
| load_fileA | Cache a single file for analysis tools (refactor_code, ask_about_code, verify_logic). Overwrites previous cache. Path is relative to server working directory (e.g. src/index.ts) or absolute (e.g. /home/user/project/src/index.ts). |
| refactor_codeA | Analyze cached file for complexity, duplication, naming, and grouping improvements. Prerequisite: load_file. Set maxSuggestions to cap output (default 10). |
| generate_documentationA | Generate documentation stubs for all public exports in a cached file. Prerequisite: load_file. Auto-infer language. |
| detect_code_smellsA | Detect structural code smells in a cached file. Prerequisite: load_file. Auto-infer language. |
| ask_about_codeA | Answer questions about a cached file. Prerequisite: load_file. Auto-infer language. |
| verify_logicA | Verify algorithms and logic in a cached file using Gemini code execution sandbox. Prerequisite: load_file. Auto-infer language. |
| web_searchA | Google Search with Grounding. Set topic to scope results; responseStyle controls output length. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| get-help | Returns full server instructions: capabilities, tools, resources, constraints, and task lifecycle. |
| review-guide | Returns a workflow guide for a specific tool and focus area. Supports auto-completion. |
| select-workflow | Returns a recommended tool pipeline based on the type of code change. Supports auto-completion. |
| analyze-file | Returns a goal-based tool pipeline for single-file analysis. Supports auto-completion. |
| tool-chain | Returns the full prerequisite chain for a given tool, including setup steps and follow-ups. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| server-instructions | Complete server usage instructions. |
| tool-catalog | Tool reference: models, params, outputs, data flow. |
| workflows | Recommended workflows and tool sequences. |
| server-config | Runtime configuration and limits. |
| diff-current | The most recently generated diff, cached by generate_diff. Read by all review tools automatically. |
| file-current | The most recently loaded source file, cached by load_file. Read by file analysis tools automatically. |
| tool-info:analyze_pr_impact | Per-tool reference: model, params, output, gotchas. |
| tool-info:analyze_time_space_complexity | Per-tool reference: model, params, output, gotchas. |
| tool-info:ask_about_code | Per-tool reference: model, params, output, gotchas. |
| tool-info:detect_api_breaking_changes | Per-tool reference: model, params, output, gotchas. |
| tool-info:detect_code_smells | Per-tool reference: model, params, output, gotchas. |
| tool-info:generate_diff | Per-tool reference: model, params, output, gotchas. |
| tool-info:generate_documentation | Per-tool reference: model, params, output, gotchas. |
| tool-info:generate_review_summary | Per-tool reference: model, params, output, gotchas. |
| tool-info:generate_test_plan | Per-tool reference: model, params, output, gotchas. |
| tool-info:load_file | Per-tool reference: model, params, output, gotchas. |
| tool-info:refactor_code | Per-tool reference: model, params, output, gotchas. |
| tool-info:verify_logic | Per-tool reference: model, params, output, gotchas. |
| tool-info:web_search | Per-tool reference: model, params, output, gotchas. |
TDQS
Scored across 13 tools
All tools have distinct purposes, clearly separated into diff-based and file-based categories. No overlapping functionality.
All tools follow a consistent verb_noun pattern in snake_case, making it easy to predict tool names.
13 tools is well-scoped for a code analysis server, covering both diff review and file analysis without being excessive.
Covers major code review aspects (diff, smells, complexity, breaking changes, test plan, docs, refactoring, verification). Could include linting or style checks but overall comprehensive.