grep_record
Performs text or regular expression searches across all parts of the fetched record (structured FHIR data + text from notes/attachments). Ideal for finding keywords or specific mentions (e.g., "diabetes", "aspirin").
How to use it
grep_record is exposed by the Health Record MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the grep_record tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL HEALTH RECORD MCP LISTINGOther tools in Health Record MCP (7)
An array of processed attachment objects, each including metadata (source resource, path, content type) and the content itself (contentBase64 for raw data, contentPlaintext for extracted text).
Executes custom JavaScript code directly on the fetched data (FHIR resources + attachments). Offers maximum flexibility for complex calculations, combining data from multiple sources, or custom formatting.
A dictionary where keys are FHIR resource types (e.g., "Patient") and values are arrays of the corresponding FHIR resources.
Executes read-only SQL SELECT queries directly against the structured FHIR data. Useful for precise lookups based on known FHIR resource structures (e.g., finding specific lab results by LOINC code).
An array of strings (e.g., ["epic", "sandbox"]) used for categorization or filtering.
Path/URL to the brand definition file (like static/brands/epic-sandbox.json).
Contains SMART on FHIR client details (clientId, scopes).