DocGraph
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOCGRAPH_DEBUG | No | Set to '1' to log JSON-RPC traffic to stderr | 0 |
| DOCGRAPH_PROJECT | No | Path to the project root to serve (overrides working directory) | |
| DOCGRAPH_NO_WATCH | No | Set to '1' to disable auto-sync file watching | 0 |
| DOCGRAPH_READ_ONLY | No | Set to '1' to enable read-only mode (no writes to index) | 0 |
| DOCGRAPH_MAX_PROJECTS | No | Maximum number of projects in LRU cache (default 16) | 16 |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| index_projectC | Index all documents in the project |
| index_fileC | Index a specific file |
| searchC | Search documents using hybrid full-text + vector search |
| exploreC | Explore a topic with surrounding context |
| get_documentC | Get a document by ID or path |
| get_relatedC | Get related documents |
| get_statsC | Get index statistics |
| list_documentsC | List all indexed documents |
| get_document_graphC | Get a document node/edge connections |
| list_projectsA | List projects with an active .docgraph index in this MCP server. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Project Documentation | All indexed project documents |
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: exploration, document retrieval, graph connections, related documents, stats, indexing, and listing. No overlaps or ambiguity.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_document, index_file, list_projects), with only a few single-verb names like explore and search, which are still clear and fit the pattern.
10 tools is well-scoped for a document indexing and exploration server, covering indexing, querying, and management without excess or deficiency.
The tool surface covers core workflows: indexing (file and project), querying (search, explore, get, related, graph), and listing. Missing update or delete operations, but these are not central to exploration-focused design.