Outline Wiki MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| READ_ONLY | No | Enable read-only mode | false |
| MAX_RETRIES | No | API retry attempts | 3 |
| OUTLINE_URL | No | Your Outline instance URL | https://app.getoutline.com |
| DISABLE_DELETE | No | Disable delete operations | false |
| OPENAI_API_KEY | No | OpenAI API key (required when ENABLE_SMART_FEATURES=true) | |
| RETRY_DELAY_MS | No | Retry delay (ms) | 1000 |
| OUTLINE_API_TOKEN | Yes | Your Outline API token | |
| ENABLE_SMART_FEATURES | No | Enable AI features | false |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_documentsC | Search documents by keyword. Supports pagination. |
| get_document_id_from_titleC | Find document ID by title. |
| list_collectionsC | Get list of all collections. |
| get_collection_structureC | Get document hierarchy within a collection. |
| list_recent_documentsC | Get list of recently modified documents. |
| get_documentC | Get full document content by document ID. |
| export_documentC | Export document in Markdown format. |
| create_documentD | Create a new document. |
| update_documentC | Update an existing document. Can append content with append mode. |
| move_documentC | Move document to another collection or under a parent document. |
| archive_documentD | Archive a document. |
| unarchive_documentB | Restore an archived document. |
| delete_documentB | Delete a document. If permanent=true, permanently delete; otherwise move to trash. |
| restore_documentC | Restore a document from trash. |
| list_archived_documentsC | Get list of archived documents. |
| list_trashC | Get list of documents in trash. |
| add_commentC | Add a comment to a document. Supports replies. |
| list_document_commentsC | Get list of comments on a document. |
| get_commentC | Get details of a specific comment. |
| get_document_backlinksC | Find other documents linking to this document. |
| create_collectionC | Create a new collection. |
| update_collectionC | Update collection information. |
| delete_collectionB | Delete a collection. All documents in the collection will also be deleted. |
| export_collectionC | Export a collection. |
| export_all_collectionsC | Export all collections. |
| batch_create_documentsC | Create multiple documents at once. |
| batch_update_documentsC | Update multiple documents at once. |
| batch_move_documentsC | Move multiple documents at once. |
| batch_archive_documentsC | Archive multiple documents at once. |
| batch_delete_documentsC | Delete multiple documents at once. |
| sync_knowledgeB | Sync documents to vector store for AI-powered search. Run this before using ask_wiki. |
| ask_wikiC | Ask a question and get an answer based on wiki content using RAG. |
| summarize_documentC | Generate an AI-powered summary of a document. |
| suggest_tagsC | Get AI-suggested tags for a document based on its content. |
| find_relatedC | Find documents semantically related to a specific document. |
| generate_diagramC | Generate a Mermaid diagram from a text description. |
| smart_statusB | Check if smart features are enabled and get index statistics. |
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 37 tools
Most tools have distinct purposes, but some overlap exists. For example, 'search_documents' and 'find_related' both involve document discovery, though 'find_related' is semantic. 'archive_document' and 'delete_document' (with permanent=false) both involve removal, but descriptions clarify differences. Overall, descriptions help, but a few tools could be confused without careful reading.
Tool names follow a highly consistent verb_noun pattern throughout, such as 'create_document', 'list_collections', 'update_document', and 'delete_collection'. All tools use snake_case, and verbs are predictable (e.g., add, archive, ask, batch, create, delete, export, get, list, move, restore, search, sync, unarchive, update). No deviations or mixed conventions are present.
With 37 tools, the count is borderline high for a wiki server, feeling heavy compared to typical well-scoped sets of 3-15 tools. While the tools cover extensive operations, it may overwhelm agents. However, given the domain's complexity, it's not extreme, but leans toward too many for optimal coherence.
The tool set provides complete CRUD/lifecycle coverage for documents and collections, including creation, reading, updating, deletion, archiving, restoration, and export. It also includes advanced features like AI-powered search, summarization, diagram generation, and batch operations. No obvious gaps exist; agents can handle all core wiki workflows without dead ends.