This MCP server implementation provides a bridge to DataBridge, enabling AI assistants to ingest and retrieve information from a local database. Developed as part of the databridge-mcp project, it offers two main tools: one for ingesting user observations with metadata, and another for retrieving relevant information based on user queries. The server uses FastMCP for efficient request handling and is designed to work with Python 3.11+. It's particularly useful for AI applications requiring persistent storage and retrieval of contextual information, supporting use cases like maintaining conversation history or building knowledge bases from user interactions. The implementation focuses on simplicity and ease of integration, making it suitable for both development and production environments.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIIngest a text document into Morphik. Parameters: content, filename (optional), metadata (optional), apiKey
Ingest a file from the server's filesystem into Morphik. Parameters: path, metadata (optional), rules (optional), folderName (optional), endUserId (optional), useColpali (optional)
Upload a file by providing its filename plus base64-encoded bytes. Parameters: filename, base64Content, metadata (optional), rules (optional), folderName (optional), endUserId (optional), useColpali (optional)
Batch ingest multiple files from the server's filesystem. Parameters: paths, metadata (optional), rules (optional), folderName (optional), endUserId (optional), useColpali (optional)
Retrieve the most relevant 'pages' (text or image chunks) for a query. Parameters: query, filters (optional), k (optional), minScore (optional), folderName (optional), endUserId (optional), useColpali/useReranking (optional), padding (optional for adjacent context)
Retrieve relevant documents from Morphik based on a query. Parameters: query, filters (optional), k (optional), minScore (optional), folderName (optional), endUserId (optional)
Search for documents by filename or title using full-text search. Parameters: query, limit (optional, 1-100), folderName (optional), endUserId (optional)
Fetch an inclusive range of pages (max 10) from a document. Parameters: documentId, startPage, endPage, folderName (optional), endUserId (optional)
Get a specific document from Morphik by ID. Parameters: documentId, apiKey
Delete a document from Morphik by ID. Parameters: documentId, apiKey
Check the processing status for an ingested document. Parameters: documentId, apiKey
View, set, or clear typed metadata filters that automatically apply to retrieval/list operations. Parameters: action, expression/rules payload, logic (optional)
Updated tool using '/documents/list_docs' with additional parameters. Parameters: skip, limit, filters/metadataFilters, get_count, folderName(s), endUserId, sortBy/sortDirection, fields
List directories that the server is allowed to access. Parameters: none
List files and subdirectories in a specific directory. Parameters: path
Search for files matching a pattern in a directory and its subdirectories. Parameters: path, pattern, excludePatterns (optional)
Get detailed information about a file or directory. Parameters: path
