docx-mcp-server
Server 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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_documentA | Reads a .docx file and returns the full text content. Use this to read, summarize, or analyze a Word document. Requires an absolute or relative path — use resolve_document first if you only have a document name. |
| search_documentA | Searches for text within a .docx file and returns matching lines with line numbers and context. Case-insensitive. Use for finding specific content within a document. |
| get_document_metadataA | Returns metadata about a .docx file including file name, size, creation date, modification date, word count, character count, and line count. Use this for document statistics or to verify a document before reading. |
| list_documentsA | Lists all .docx files in a directory. Use this to discover what Word documents are available in a specific folder. Returns full paths for each .docx file found. |
| resolve_documentA | Finds .docx files by friendly name and optional location. Use this when a user refers to a document by name (e.g., 'the report on my desktop') rather than by full path. Returns the resolved absolute path, a list of candidates if ambiguous, or helpful error if not found. After resolving, use read_document or search_document with the resolved path. |
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 5 tools
Each tool has a clearly distinct purpose: reading full content, searching with context, retrieving metadata, listing files, and resolving paths. There is no meaningful overlap—even list_documents and resolve_document serve different discovery functions.
All tools follow a consistent verb_noun snake_case pattern (read_document, search_document, get_document_metadata, list_documents, resolve_document). The singular/plural distinction is natural and does not break the convention.
Five tools is well within the 3-15 ideal range and covers the core operations needed for a read-only docx server without bloat or sparseness.
For the stated purpose of reading, searching, and analyzing Word documents, the tool surface is complete. It covers discovery (list, resolve), access (read), search, and metadata, forming a coherent workflow with no dead ends.