get_docset
Get DocSet
Retrieve detailed metadata for a specific DocSet, including its schema, properties, and document count.
Ask your agent in plain language. Each of these maps to a real tool on the server.
get_docset
Retrieve detailed metadata for a specific DocSet, including its schema, properties, and document count.
update_docset
Update a DocSet's metadata including name and custom properties. Note that fields like prompts are replaced entirely (not merged).
list_docsets
List all DocSets in the account. DocSets are collections of parsed documents, similar to folders. Supports filtering by name and pagination.
delete_docset
Delete a DocSet and all its documents. This action is irreversible.
search_documents
Search over documents and metadata in a DocSet using vector, keyword, lexical, or hybrid search. Returns matching documents or elements (chunks) based on search criteria. Supports property-based filtering to narrow results, and can return results at the document level or the element (chunk) level.
generate_query_plan
Generate an execution plan for a natural language query without running it. Returns the logical plan that shows what operations would be performed, allowing inspection and modification before execution.
download_document
Download the original source file of a stored document. Call list_docsets and list_documents to discover the DocSet and document IDs.
add_document
Parse a document from a URL and store it in an existing DocSet. The DocSet schema is used to extract document properties. Call list_docsets to discover the destination.
extract_properties
Extract metadata properties from all documents in a DocSet using GenAI. Properties are key-value pairs extracted by an LLM based on a user-defined schema. Define the properties to extract including name, type, description, and optional defaults. The LLM will analyze each document and extract the requested values.
delete_document
Delete a document from a DocSet. This removes the document and all its parsed data permanently.
update_document_properties
Update metadata properties on a specific document using JSON Patch operations. Aryn currently supports only replacing property values.
delete_properties
Remove extracted metadata properties from all documents in a DocSet. Specify the property names to delete.
list_documents
List all documents stored in a specific DocSet. Returns document metadata including IDs and properties. Supports pagination for large collections.
suggest_properties
Ask Aryn to analyze documents in a DocSet and suggest a schema of properties that could be extracted. Useful when you don't know what metadata is available in your documents.
get_document
Retrieve a parsed document from a DocSet, including its metadata and optionally its parsed elements (chunks). Use this to inspect the structured content of a previously parsed document.
execute_query_plan
Execute a logical plan returned by generate_query_plan against a DocSet. This allows an inspected or modified plan to be run without generating a new one.
create_docset
Create a new DocSet to store and organize parsed documents. Optionally define a schema for metadata properties and custom properties.
run_query
Run a natural language query against a DocSet using Aryn's Deep Analytics engine. The query engine combines GenAI reasoning with database and LLM-based operators to analyze documents. Supports both RAG-mode queries (retrieval-augmented generation) and full deep analytics queries with multi-step execution plans.
parse_document
Parse and segment a document into structured output using Aryn DocParse. Supports 30+ file formats including PDF, DOCX, PPTX, and more. Provide a document via URL and configure parsing options including text extraction mode, table extraction, image summarization, OCR language, output format, and chunking. Returns structured elements with labeled bounding boxes for titles, tables, images, and text, plus a downloadable JSON, Markdown, or HTML file. Parsing may also store the document in a DocSet.
Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.
{"mcpServers": {"metorial": {"url": "<your-magic-mcp-url>"}}}
claude mcp add --transport http metorial <your-magic-mcp-url>
codex mcp add metorial --url <your-magic-mcp-url>codex mcp login metorial
One governed layer for every app your agents reach, not a separate connector per tool.
Parse, segment, and extract structured data from 30+ document types including PDFs and Office files. Convert complex documents into structured JSON, Markdown, or HTML with labeled bounding boxes for titles, tables, images, and text. Extract tables with cell-level content, run OCR in multiple languages, and summarize images. Store parsed documents in DocSets, extract metadata properties as key-value pairs using GenAI, and search across documents and metadata with vector and keyword search. Analyze document collections using natural language queries in deep analytics workspaces. Supports chunking strategies, asynchronous processing for large collections, and property-based filtering.
Common questions about connecting Aryn to AI agents with Metorial.