Code Search MCP 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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| view_files_outlinesA | [Deep Code Insight] Batch extraction of file structural outlines. The best tool for exploring global project structures, enhanced for Java with Spring annotation parsing (e.g., identifying API routes, Service components). Use this to concurrently fetch outlines for multiple files when building project maps, tracing interface logic, or performing large-scale code reviews. |
| view_code_itemsA | [Precise Code Retrieval] Best for cases where the file path and item name are known. Batch returns full definition blocks for classes/methods/functions. If the input is a Java interface and implementations exist, it will attempt to traverse to Impl classes and return same-named method snippets (multiple implementations are supported and labeled). It also parses fields referenced in the method snippet to infer their type-to-class paths. Ideal for interface/implementation comparison, fast location of key methods, and precise extraction before call-chain analysis; if the path or name is unknown, use file search tools first. |
| view_files_full_contextA | Code analysis tool with 'Panoramic Vision'. Optimized for Java/Spring to provide a bird's-eye view across multiple files. Key Effects:
|
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 3 tools
The tools have distinct primary purposes: view_code_items for precise retrieval of known items, view_files_full_context for panoramic analysis with auto-expansion, and view_files_outlines for structural exploration. However, view_files_full_context and view_files_outlines both involve file-level analysis and could be confused in some scenarios, though their descriptions clarify different focuses (context vs. outlines).
All tool names follow a consistent verb_noun pattern with 'view_' prefix and descriptive suffixes (code_items, files_full_context, files_outlines). The naming is uniform and predictable, making it easy to understand the tool set's structure at a glance.
With 3 tools, the count is appropriate for a code search server, covering precise retrieval, contextual analysis, and structural outlines. It is slightly lean but reasonable, as each tool serves a clear and distinct function without obvious redundancy, though a few more specialized tools might enhance coverage.
The tools cover key aspects of code search and analysis, including retrieval, context, and structure, but there are notable gaps. For example, there is no tool for searching code by content (e.g., text search) or for updating/modifying code, which are common in code-related workflows. The surface is functional but incomplete for a full code interaction domain.