Aryn MCP server

Connect Aryn to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Aryn MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the get doc set tool in Aryn
  • Use the update doc set tool in Aryn
  • Use the list doc sets tool in Aryn
  • Use the delete doc set tool in Aryn
  • Use the search documents tool in Aryn
  • Use the generate query plan tool in Aryn

Supported Tools

get_docset

Get DocSet

Retrieve detailed metadata for a specific DocSet, including its schema, properties, and document count.

update_docset

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 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 DocSet

Delete a DocSet and all its documents. This action is irreversible.

search_documents

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 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 Original 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

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 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 Document

Delete a document from a DocSet. This removes the document and all its parsed data permanently.

update_document_properties

Update Document Properties

Update metadata properties on a specific document using JSON Patch operations. Aryn currently supports only replacing property values.

delete_properties

Delete Properties

Remove extracted metadata properties from all documents in a DocSet. Specify the property names to delete.

list_documents

List Documents

List all documents stored in a specific DocSet. Returns document metadata including IDs and properties. Supports pagination for large collections.

suggest_properties

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

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 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 DocSet

Create a new DocSet to store and organize parsed documents. Optionally define a schema for metadata properties and custom properties.

run_query

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 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.

Connect Aryn to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Aryn in Metorial. In your Metorial portal, enable the Aryn MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Aryn tools.

Run Aryn through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Aryn and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Aryn tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Aryn

Notion

Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Confluence

Create, read, update, and delete pages, blog posts, comments, and attachments in Confluence spaces. Manage spaces, permissions, labels, and content restrictions. Search content using Confluence Query Language (CQL). Upload and download file attachments with versioning. Manage users, groups, and group memberships. Create and manage whiteboards, databases, folders, and templates. View and update inline tasks. Access audit logs.

Technical notes for Aryn

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.

Frequently asked questions

Common questions about connecting Aryn to AI agents with Metorial.

  1. How many tools does the Aryn MCP server have?
    The Aryn MCP server exposes 19 tools, including Get DocSet, Update DocSet, List DocSets. Each one is governed and traced through Metorial.
  2. Aryn exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Aryn MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Aryn and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Aryn MCP server yourself or use the hosted gateway.

Connect Aryn to production AI agents

See how Metorial gives your team governed access to Aryn, with tracing and security controls built in.