Reflex
OfficialServer 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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_codeA | Search code for a literal pattern: every match with path, line and preview (for path and line only, list_locations is cheaper). Whole identifiers by default; contains:true for substrings; symbols:true for definitions only (kind narrows them). Answer: {columns, rows} (each row aligns with columns) plus pagination; when has_more, fetch the next page with offset. total_count is exact only when total_is_exact. |
| search_regexB | Search code with a regular expression (Rust regex): alternation, classes, anchors, e.g. |
| list_locationsA | Where does X occur? Every match as {path, line}: the cheapest search, no limit. preview:true adds each matching line (trimmed, 120 chars). Same matching as search_code. |
| find_referencesA | A symbol's definition and every usage in one call, in code files only; matches in strings and comments are left out (include_strings:true keeps them). Answer: {definition, references, total_references, returned_count, filtered_out, pagination}; mode:"count" returns the count after filtering. |
| search_astA | Tree-sitter structural search, e.g. |
| get_dependenciesA | The imports of a file: path, line, internal/external/stdlib. reverse:true lists the files that import it instead; depth:N follows imports N levels (a list of {path, depth}). Static imports only; path may be a fragment or file name. |
| analyzeA | Import-graph analysis. kind: summary (counts), hotspots (most-imported files), circular (import cycles), unused (files nothing imports; entry points included), islands (disconnected groups). Answers are paginated with limit/offset. |
| gather_contextC | Project overview: structure, file types, frameworks, entry points, test layout, config files. Pass flags to pick sections (default: all). |
| index_projectA | Force an index run. Rarely needed: every tool updates the index before it answers. force:true rebuilds a corrupted index. |
| check_index_statusA | Report whether the index matches the files on disk, without updating it. Rarely needed: every other tool updates the index first. |
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 10 tools
Most tools target distinct capabilities, but the five search-related tools (search_code, search_regex, list_locations, search_ast, find_references) overlap in purpose. The descriptions clarify boundaries—list_locations is the cheapest path/line search, search_ast is structural, find_references combines definition and usages—but an agent still must read carefully to choose correctly.
Tool names follow a mostly consistent verb_noun snake_case pattern: search_code, get_dependencies, list_locations, find_references, gather_context, index_project, check_index_status. The bare verb 'analyze' is a minor deviation from the pattern, but overall naming is predictable and readable.
Ten tools is well-scoped for a code intelligence server, covering search, dependencies, references, import analysis, project overview, and index management. Each tool has a clear role, and the index-management tools are lightweight and rarely needed but justified for reliability.
The surface covers core code-intelligence workflows: literal/regex/structural search, dependency lookup, reference finding, import-graph analysis, and project overview. However, there is no direct file-content read or symbol-listing tool, which are minor gaps that agents can partially work around using search previews and gather_context.