smart-coding-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SMART_CODING_DEVICE | No | Inference device (`cpu`, `webgpu`, `auto`) | cpu |
| SMART_CODING_VERBOSE | No | Enable detailed logging | false |
| SMART_CODING_BATCH_SIZE | No | Files to process in parallel | 100 |
| SMART_CODING_CHUNK_SIZE | No | Lines of code per chunk | 25 |
| SMART_CODING_MAX_RESULTS | No | Max search results returned | 5 |
| SMART_CODING_WATCH_FILES | No | Auto-reindex on file changes | false |
| SMART_CODING_CHUNKING_MODE | No | Code chunking (`smart`, `ast`, `line`) | smart |
| SMART_CODING_MAX_FILE_SIZE | No | Max file size in bytes (1MB) | 1048576 |
| SMART_CODING_EMBEDDING_MODEL | No | AI embedding model | nomic-ai/nomic-embed-text-v1.5 |
| SMART_CODING_MAX_CPU_PERCENT | No | Max CPU usage during indexing (10-100%) | 50 |
| SMART_CODING_SEMANTIC_WEIGHT | No | Weight for semantic vs exact matching | 0.7 |
| SMART_CODING_AUTO_INDEX_DELAY | No | Delay before background indexing (ms), `false` to disable | 5000 |
| SMART_CODING_EXACT_MATCH_BOOST | No | Boost multiplier for exact text matches | 1.5 |
| SMART_CODING_EMBEDDING_DIMENSION | No | MRL dimension (64, 128, 256, 512, 768) | 128 |
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 |
|---|---|
| a_semantic_searchA | Performs intelligent hybrid code search combining semantic understanding with exact text matching. Ideal for finding code by meaning (e.g., 'authentication logic', 'database queries') even with typos or variations. Returns the most relevant code snippets with file locations and line numbers. |
| b_index_codebaseA | Manually trigger a full reindex of the codebase. This will scan all files and update the embeddings cache. Useful after large code changes or if the index seems out of date. |
| c_clear_cacheA | Clears the embeddings cache, forcing a complete reindex on next search or manual index operation. Useful when encountering cache corruption or after major codebase changes. |
| d_check_last_versionA | Get the latest version of a library/package from its official registry. Supported ecosystems: npm (JS/TS), PyPI (Python), Packagist (PHP), Crates.io (Rust), Maven (Java/Kotlin), Go, RubyGems, NuGet (.NET), Hex (Elixir), CRAN (R), CPAN (Perl), pub.dev (Dart), Homebrew (macOS), Conda (Python/R), Clojars (Clojure), Hackage (Haskell), Julia, Swift PM, Chocolatey (Windows). Returns the version string to help you avoid using outdated dependencies. |
| e_set_workspaceA | Change the project workspace path at runtime. Use this when you detect the current workspace is incorrect or you need to switch to a different project directory. Creates cache folder automatically and optionally re-indexes the new workspace. |
| f_get_statusA | Get comprehensive status information about the Smart Coding MCP server. Returns version, workspace path, model configuration, indexing status, and cache information. Useful for understanding the current state of the semantic search system. |
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 6 tools
Each tool has a clearly described purpose and most are easy to distinguish. The main ambiguity is between b_index_codebase and c_clear_cache, since both can result in a rebuilt embedding index, but their described triggers differ enough to avoid serious confusion.
The names use consistent snake_case and mostly follow a verb_noun pattern, but the arbitrary a_, b_, c_ prefixes are not semantically meaningful and a_semantic_search breaks the verb_noun pattern by leading with an adjective. The overall style is readable but mixes conventions.
Six tools is a reasonable size for a focused semantic code search server. However, d_check_last_version is unrelated to the core semantic-search/indexing workflow, so the tool set is slightly less focused than it could be.
The core workflow is well covered: workspace setup, indexing, cache invalidation, semantic search, and server status. Minor gaps exist around configuration control or more granular index inspection, but agents can complete the primary tasks without dead ends.