code-index-pg
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Base URL of the Ollama service used for embeddings. | http://localhost:11434 |
| CODEINDEX_PROJECT | No | Active project path to index. If unset, it can be set at runtime via the set_project_path tool. | |
| CODEINDEX_EMBED_MODEL | No | Embedding model name to use with Ollama. Must match pgvector dimensions (1024). | bge-m3 |
| CODEINDEX_DATABASE_URL | No | PostgreSQL connection string for the code index database (with pgvector). | postgres://postgres:postgres@127.0.0.1:5432/codeindex |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| set_project_pathC | Index a project directory and make it the active project. |
| update_indexA | Incremental update: index missing files, drop deleted ones (no re-embed). |
| search_codeB | Search symbols and files by literal, regex, or fuzzy match. |
| search_semanticA | Search code by meaning using embeddings (bge-m3 via Ollama). |
| callers_ofB | List symbols that call the given symbol. |
| callees_ofA | List symbols called by the given symbol. |
| impact_analysisB | 2-level recursive callers and affected files for a symbol. |
| find_filesC | Find files by glob pattern. |
| get_symbol_bodyA | Get the signature, docstring and location of a symbol. |
| get_file_summaryB | Summarize a file: language, line count, symbols. |
| get_statusA | Show indexed projects and counts. |
| remove_projectA | Remove an indexed project and all its data (cascade). |
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 12 tools
Each tool targets a distinct operation: indexing, searching (literal vs semantic), graph queries (callers/callees), file operations, and project management. No two tools appear to overlap in purpose.
Most tool names follow a clear verb_noun pattern (set_project_path, search_code, get_status). Minor exception: 'callers_of' and 'callees_of' use a different prepositional style, but still readable and predictable.
12 tools is well within the ideal range for a code indexing/search server. Each tool serves a distinct function needed for code navigation and project management, with no redundancy.
The surface covers the full lifecycle: project setup, incremental updates, multiple search modes, symbol graph queries, file and symbol detail, and project removal. Missing features like batch re-index or cross-project search are minor and not essential.