office-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
} |
| 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 |
|---|---|
| word_analyzeC | Analyze a Word document structure. Returns text index for word_replace. Addressing scheme for replacements: p:{i} → body paragraph c:{t}:{r}:{c} → entire cell (auto line-map, use \n for multi-line) c:{t}:{r}:{c}:{p} → specific paragraph inside a cell Optional format hints (in fmt_hints param): "_fmt:p:{i}" → {"runs": [{"text": "中一", "underline": true}]} |
| word_replaceB | Replace text in a Word document, preserving all formatting. |
| word_clone_templateA | Clone a table-template Word doc and replace fields. Preserves all formatting. (Legacy tool — for new templates, prefer word_analyze + word_replace) |
| word_read_documentA | Read a Word document: paragraphs + tables. |
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 4 tools
word_read_document, word_analyze, and word_replace have distinct read/analyze/replace purposes, but word_clone_template overlaps with the word_analyze + word_replace workflow as a legacy alternative, creating moderate ambiguity about which tool to choose for template replacement.
All tool names share the word_ prefix and use lower_snake_case, but word_analyze and word_replace omit an explicit object while word_clone_template and word_read_document include one, so the verb_object pattern is inconsistently applied.
With 4 tools, the server is compact and near the ideal size for a focused Word-document manipulation purpose; the legacy tool slightly inflates the count without adding a genuinely new capability.
The set covers reading, structural analysis, text replacement, and template cloning, which covers the main document-editing workflows. Missing operations like creating blank documents or managing document-level formatting are minor given the server's apparent templating focus.