Ask your agent in plain language. Each of these maps to a real tool on the server.
list_objects
List objects from a collection using the REST API. Supports pagination via limit/offset or cursor-based pagination. Use this for simple object retrieval without search ranking; for search use the **Search Objects** tool instead.
search_objects
Search for objects in a Weaviate collection using various search methods: - **nearText**: Semantic search using natural language concepts (requires a text vectorizer) - **nearVector**: Search by raw vector similarity - **nearObject**: Find objects similar to an existing object - **hybrid**: Combined vector + keyword search with configurable weighting - **bm25**: Pure keyword search using BM25 ranking Exactly one search method must be provided. Results can be filtered with a where clause and paginated with limit/offset.
get_collection
Retrieve the full schema definition of a specific collection, including its properties, vectorizer configuration, module settings, vector index type, and multi-tenancy configuration.
update_object
Update an existing object's properties in a collection. Use **replaceAll** mode to replace all properties (PUT), or **patch** mode to merge only the provided properties (PATCH).
create_collection
Create a new collection (class) in Weaviate with its schema definition. Configure properties, vectorizer, generative module, vector index settings, and multi-tenancy. The vectorizer cannot be changed after creation. Generative configuration is mutable on supported server versions.
aggregate_collection
Run aggregation queries over a collection to compute metrics like counts, sums, averages, min/max, top occurrences, and more. Supports grouping by a property and filtering with a where clause. Provide the GraphQL metric selection and optional aggregation filters. Requires GraphQL to be enabled on the cluster.
batch_delete_objects
Delete multiple objects from a collection that match a given where filter. Supports dry-run mode to preview which objects would be deleted without actually removing them.
list_collections
List all collections (classes) in the Weaviate instance. Returns each collection's name, description, properties, vectorizer, and configuration.
update_collection
Update an existing collection's settings or add new properties. You can update the description, inverted index config, replication config, and add new properties. The vectorizer cannot be changed and properties cannot be removed. Replication factor changes require replica movement.
get_object
Retrieve a specific object from a collection by its UUID. Optionally include vector embeddings in the response.
cluster_status
Get comprehensive information about the Weaviate instance including version, module list, cluster health, and node statuses with shard and object counts.
generative_search
Perform Retrieval Augmented Generation (RAG) by searching a collection and prompting an LLM with the retrieved results. Requires a generative module configured on the collection. Two generation modes: - **Single prompt**: Generates a response for each result individually, using object properties via `{propertyName}` template syntax. - **Grouped task**: Generates one response from all results combined, using all or selected properties as context.
batch_create_objects
Import multiple objects into one or more collections in a single batch request. Optionally include pre-computed vectors for each object. Supports multi-tenant collections.
create_object
Create a new data object in a Weaviate collection. Optionally provide a pre-computed vector embedding, or let the configured vectorizer generate one automatically. Supports multi-tenant collections by specifying the tenant name.
delete_object
Delete a specific object from a collection by its UUID. This permanently removes the object and its vector embedding.
delete_collection
Permanently delete a collection and all its objects from the Weaviate instance. This action cannot be undone.
manage_backup
Create, restore, or check the status of a Weaviate backup. Supports S3, GCS, Azure, and filesystem backends. - **create**: Start a new backup of all or selected collections. - **restore**: Restore a previously created backup. - **status**: Check the status of a backup or restore operation.
manage_tenants
Manage tenants in a multi-tenant collection. Supports listing, adding, updating status, and removing tenants. Each tenant provides data isolation with its own shard. Tenant statuses: **ACTIVE** (available), **INACTIVE** (stored locally but not loaded), **OFFLOADED** (moved to cold storage).
manage_references
Add or remove cross-references between objects across collections. Cross-references create links between objects, enabling graph-like data traversal.
get_current_user
Get the authenticated Weaviate username, assigned roles, and groups. Requires a server that supports the current-user endpoint.
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.
Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.
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.
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.
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.
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.
Upload, download, create, copy, move, rename, trash, and permanently delete files and folders in Google Drive. Search for files using complex queries filtering by name, MIME type, owner, modification date, labels, and other metadata. Share files and folders with specific users, groups, or domains with role-based permissions (owner, writer, commenter, reader). Manage shared drives and their members. Export Google Workspace files (Docs, Sheets, Slides) to standard formats like PDF, DOCX, and XLSX. Track file revision history and restore earlier versions. Create, read, update, and delete threaded comments and replies on files. Read label definitions and search files by label. Browse the Drive apps installed for your account. Store app-specific data in a hidden per-user folder.
Store, search, and manage data objects with vector embeddings in an AI-native vector database. Create and configure collections with vectorizers and generative modules. Import objects individually or in batches with automatic or custom vector embeddings. Perform semantic (vector) search, hybrid search combining vector and keyword (BM25) matching, and filtered queries. Execute retrieval augmented generation (RAG) using integrated LLMs. Aggregate data across collections for statistical metrics. Manage multi-tenant data isolation, create and restore backups, and discover the authenticated user identity. Monitor cluster health and node status.
Common questions about connecting Weaviate to AI agents with Metorial.
