Code Indexing MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| INCODE_OFFLINE | No | Set to '1' to disable network access (model download will fail if not cached) | 0 |
| INCODE_DATA_DIR | No | Override the platform-specific data directory for index storage | |
| INCODE_CACHE_DIR | No | Override the platform-specific cache directory for model downloads | |
| INCODE_AUTO_INDEX | No | Set to '0', 'false', or 'no' to disable automatic indexing of workspace roots | 1 |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| init_projectD | – |
| index_projectD | – |
| project_statusD | – |
| list_projectsD | – |
| remove_projectD | – |
| search_codeD | – |
| find_symbolD | – |
| file_outlineD | – |
| get_chunkD | – |
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 9 tools
Most tools clearly target distinct actions: project lifecycle (init, index, status, list, remove) versus code querying (find_symbol, search_code, file_outline, get_chunk). init_project and index_project could be confused without descriptions, and find_symbol/search_code overlap slightly, but their intended scopes are still distinguishable.
All names use lowercase snake_case with mostly verb_noun construction like init_project, list_projects, remove_project, search_code, and get_chunk. A couple are noun phrases such as project_status and file_outline, which deviate slightly from the dominant pattern, but the naming remains predictable and readable.
Nine tools is well within the ideal range for a focused code-indexing server. Each tool covers a necessary part of the workflow: project setup, indexing, status, discovery, removal, and code retrieval/exploration.
The tool surface covers the main project lifecycle and core code-search/exploration needs. Obvious gaps like symbol references, project updates, or index rebuilding are minor and can typically be worked around using the existing tools.