Xcode Index MCP
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 |
|---|---|
| load_indexB | Load the IndexStore for a project from the Derived Data folder. Args: projectName: Name of the project to load the index for. Returns: bool: True if the index was loaded successfully, False otherwise. |
| symbol_occurrencesC | Get symbols occurring at a specific location in a file. Args: filePath: Absolute path to the file lineNumber: Line number in the file Returns: Dict containing symbol information at the specified location |
| get_occurrencesB | Get all occurrences of a symbol by its USR. Args: usr: The USR (Unified Symbol Resolution) of the symbol roles: The roles to search for (must be "reference" or "definition") Returns: Dict containing all occurrences of the symbol |
| search_patternB | Search for symbol occurrences matching a pattern. Args: pattern: The pattern to search for options: Optional list of search options. Valid options are: - anchorStart: Match pattern at start of symbol name - anchorEnd: Match pattern at end of symbol name - subsequence: Match pattern as subsequence (not exact match) - ignoreCase: Case-insensitive matching Returns: Dict containing matching canonical symbol occurrences |
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 4 tools
The tools have distinct primary purposes: loading an index, searching by pattern, retrieving by USR, and looking up by file location. However, get_occurrences and symbol_occurrences could be slightly confused as both retrieve symbol occurrences, though they use different input parameters (USR vs. file location).
All tool names follow a consistent snake_case verb_noun pattern (e.g., load_index, search_pattern, get_occurrences, symbol_occurrences). The naming is predictable and readable throughout the set.
With 4 tools, the count is reasonable for an index query server, covering core operations like loading, searching, and retrieving symbols. It might be slightly thin if advanced features like filtering or batch operations are needed, but it's well-scoped for basic functionality.
The tools cover key index operations: loading, pattern search, and symbol retrieval by USR or location. However, there are notable gaps, such as no ability to update or delete index data, list available projects, or handle errors more granularly, which could limit agent workflows in complex scenarios.