animus-document-engine
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 |
|---|---|
| render_documentA | Render a structured spec into real Office bytes (xlsx/pptx/docx). Returns the file as base64. This is the primary authoring path: an agent writes a spec, this produces the openable file. |
| parse_documentA | Read an existing file (base64) back into a spec. v1 supports xlsx (data + headers). pptx/docx high-fidelity parsing is deferred to a future Python worker and will error here. |
| apply_editsA | Apply a list of edit ops (replace | set | append | remove) to a spec and return the edited, re-validated spec. The caller re-renders the result. Because the spec is the source of truth, editing the spec (not the bytes) is lossless. |
| convert_documentA | Convert a document (base64) to another format via LibreOffice-WASM — e.g. to 'pdf', 'html', 'png'. Returns the converted bytes as base64. Fidelity-critical, no native LibreOffice needed. |
| preview_documentA | Produce a preview for the in-browser viewer: a full-fidelity PDF (kind='pdf', default) or a single-page PNG thumbnail (kind='png'). Returns base64. Powers the board's document preview. |
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 targets a distinct operation: editing a spec, converting format, parsing, previewing, and rendering. No overlap or ambiguity.
Four tools follow a consistent 'verb_document' pattern, but 'apply_edits' breaks the pattern slightly. Still all are verb_noun and clear.
With 5 tools, the set is well-scoped for a document engine covering editing, conversion, parsing, preview, and rendering without bloat.
Core workflows are covered: create (render from spec), edit (apply_edits), convert, parse, preview. Minor gap: no tool to initialize a new spec, but agent can write one directly.