brainfish_search_documents
Semantic search across your knowledge base
LABSCO SUMMARY
Reading the sessions is what closes the loop — the gaps in your help centre are in the transcripts.
Most knowledge-base servers stop at read and write. Here an agent can search what customers actually asked, read a conversation with its feedback, then generate an article suggestion and write the document — the whole cycle from complaint to published answer, without anyone exporting a CSV. The citation-scoped answer tool is the other careful piece: answers can be restricted to particular collections, so internal notes do not end up quoted to a customer.
What it is
Brainfish's endpoint over their support knowledge base. Twenty-four tools in four groups: documents, collections and catalogs, AI answering, and the conversation history from their chat widget.
What you get
- Documents: semantic search, fetch by ID or slug, list, create, update, move between collections, soft or permanent delete
- Collections and catalogs — create, update, delete, and full content sync into a catalog
- brainfish_generate_user_answer — an AI answer with source citations, optionally scoped to particular collections
- brainfish_generate_article_suggestion — asynchronous suggestions for articles the knowledge base is missing
- Sessions: search conversations, read the full detail with feedback and analytics, or the chronological event timeline
Requirements
OAuth 2.1 with the full discovery set, or a static bearer token beginning bf_api_. The server is documented as stateless; data residency and customer-managed keys are enterprise options.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Finding what the help centre is missing
Search the chat sessions for repeated questions, read one in full with its feedback, then generate an article suggestion.
02
Publishing the answer
Create the document in the right collection and set its publish status in one pass.
03
Answering with sources
Generate an answer scoped to the public collections, with citations attached.
04
Reorganising without losing anything
Move documents between collections and soft-delete rather than removing outright.
24 tools
Listed in project docs. Your client may show a different list.
brainfish_get_document
Get full document content by ID or URL slug
brainfish_list_documents
List documents with filtering and pagination
brainfish_create_document
Create a new document in a collection
brainfish_update_document
Update title, content, or publish status
brainfish_move_document
Move a document to another collection or parent document
brainfish_delete_document
Soft-delete (or permanently delete) a document
brainfish_generate_article_suggestion
Trigger AI-powered article suggestions from content (async)
brainfish_list_collections
List all accessible collections
brainfish_get_collection
Get collection details by ID
brainfish_create_collection
Create a new collection
brainfish_update_collection
Update collection name, description, visibility
brainfish_delete_collection
Delete a collection and all its documents
brainfish_generate_user_answer
Generate an AI answer with source citations, optionally scoped to specific collections; returns JSON with answer/citations/conversationId/handoff
brainfish_generate_follow_ups
Generate follow-up questions for a conversation
brainfish_list_catalogs
List all catalogs with optional filtering
brainfish_get_catalog
Get catalog details and content count
brainfish_create_catalog
Create a new catalog
brainfish_sync_catalog_content
Full sync of content files to a catalog
brainfish_search_sessions
Search chat sessions by query text and filters
brainfish_get_session
Get full conversation detail (queries, answers, feedback, analytics)
brainfish_get_session_timeline
Get chronological event timeline for a conversation
brainfish_generate_session_insights
Generate structured LLM diagnosis of a session
brainfish_validate_token
Validate your API token and return user/team info
BEFORE YOU INSTALL
What to know first
Tools you get
24 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- OAuth 2.1 (full MCP auth spec: /.well-known/oauth-authorization-server, /authorize, /token, /register) or static Bearer API token (bf_api_...)
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://mcp.brainfi.shRequirements
- OAuth 2.1 (full MCP auth spec: /.well-known/oauth-authorization-server, /authorize, /token, /register) or static Bearer API token (<YOUR_API_KEY>)
