Weaviate

Weaviate MCP Server for Cloudflare Workers

Available Tools

44 tools available in the Weaviate MCP server. Each tool can be called by AI assistants to perform specific actions.

weaviate_create_backup

Create a backup of Weaviate data.

Backups can be stored in different backends (filesystem, s3, gcs, azure).

Args:

backend: Backup backend (filesystem, s3, gcs, azure)
backupId: Unique identifier for this backup
include: Array of class names to include (optional, default: all)
exclude: Array of class names to exclude (optional)

Returns the backup status.

{
  "type": "object",
  "required": [
    "backend",
    "backupId"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "backend": {
      "enum": [
        "filesystem",
        "s3",
        "gcs",
        "azure"
      ],
      "type": "string",
      "description": "Backup storage backend"
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Classes to exclude"
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Classes to include"
    },
    "backupId": {
      "type": "string",
      "description": "Unique backup identifier"
    }
  }
}

weaviate_get_backup_status

Get the status of a backup operation.

Args:

backend: Backup backend (filesystem, s3, gcs, azure)
backupId: Backup identifier

Returns the current backup status.

{
  "type": "object",
  "required": [
    "backend",
    "backupId"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "backend": {
      "enum": [
        "filesystem",
        "s3",
        "gcs",
        "azure"
      ],
      "type": "string",
      "description": "Backup storage backend"
    },
    "backupId": {
      "type": "string",
      "description": "Backup identifier"
    }
  }
}

weaviate_restore_backup

Restore data from a backup.

Args:

backend: Backup backend (filesystem, s3, gcs, azure)
backupId: Backup identifier to restore from
include: Array of class names to include in restore (optional, default: all)
exclude: Array of class names to exclude from restore (optional)

Returns the restore operation status.

{
  "type": "object",
  "required": [
    "backend",
    "backupId"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "backend": {
      "enum": [
        "filesystem",
        "s3",
        "gcs",
        "azure"
      ],
      "type": "string",
      "description": "Backup storage backend"
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Classes to exclude from restore"
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Classes to include in restore"
    },
    "backupId": {
      "type": "string",
      "description": "Backup identifier"
    }
  }
}

weaviate_get_restore_status

Get the status of a restore operation.

Args:

backend: Backup backend (filesystem, s3, gcs, azure)
backupId: Backup identifier

Returns the current restore status.

{
  "type": "object",
  "required": [
    "backend",
    "backupId"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "backend": {
      "enum": [
        "filesystem",
        "s3",
        "gcs",
        "azure"
      ],
      "type": "string",
      "description": "Backup storage backend"
    },
    "backupId": {
      "type": "string",
      "description": "Backup identifier"
    }
  }
}

weaviate_cancel_backup

Cancel an in-progress backup or restore operation.

Args:

backend: Backup backend (filesystem, s3, gcs, azure)
backupId: Backup identifier to cancel

Returns confirmation of cancellation.

{
  "type": "object",
  "required": [
    "backend",
    "backupId"
  ],
  "properties": {
    "backend": {
      "enum": [
        "filesystem",
        "s3",
        "gcs",
        "azure"
      ],
      "type": "string",
      "description": "Backup storage backend"
    },
    "backupId": {
      "type": "string",
      "description": "Backup identifier"
    }
  }
}

weaviate_deactivate_tenants

Deactivate (cool down) tenants to reduce resource usage.

Deactivated tenants are still stored but not loaded into memory. This is a convenience method that sets tenant status to INACTIVE.

Args:

className: Name of the multi-tenant class
tenantNames: Array of tenant names to deactivate

Returns confirmation of deactivation.

{
  "type": "object",
  "required": [
    "className",
    "tenantNames"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "tenantNames": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tenant names to deactivate"
    }
  }
}

weaviate_batch_create

Create multiple objects in a single batch request.

This is the most efficient way to import large amounts of data.

Args:

objects: Array of objects to create, each with:
- class: Class name
- properties: Object properties
- id: Optional UUID
- vector: Optional custom vector
- tenant: Optional tenant name

Returns the batch operation results.

{
  "type": "object",
  "required": [
    "class",
    "properties"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID)"
    },
    "class": {
      "type": "string",
      "description": "Class name"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "vector": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Custom vector"
    },
    "properties": {
      "type": "object",
      "description": "Object properties"
    }
  }
}

weaviate_batch_delete

Delete multiple objects matching a filter in a single batch request.

Args:

className: Name of the class
where: Where filter to match objects for deletion
dryRun: If true, only report how many would be deleted without actually deleting
output: Output verbosity ('minimal' or 'verbose')

Returns the deletion results.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "dryRun": {
      "type": "boolean",
      "default": false,
      "description": "Dry run mode (no actual deletion)"
    },
    "output": {
      "enum": [
        "minimal",
        "verbose"
      ],
      "type": "string",
      "default": "minimal",
      "description": "Output verbosity"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_batch_add_references

Add multiple cross-references in a single batch request.

Args:

references: Array of references to add, each with:
- from: Source beacon (weaviate://localhost/ClassName/uuid/propertyName)
- to: Target beacon (weaviate://localhost/ClassName/uuid)

Returns the batch operation results.

{
  "type": "object",
  "required": [
    "to"
  ],
  "properties": {
    "to": {
      "type": "string",
      "description": "Target beacon (weaviate://localhost/ClassName/uuid)"
    }
  }
}

weaviate_create_classification

Start a classification task to automatically classify objects.

Classification types:

knn: k-nearest neighbors based on vector similarity
text2vec-contextionary-contextual: Contextual classification using contextionary
zeroshot: Zero-shot classification

Args:

type: Classification type (knn, text2vec-contextionary-contextual, zeroshot)
className: Class to classify objects in
classifyProperties: Properties to classify (reference properties)
basedOnProperties: Properties to base classification on
k: Number of neighbors for knn (default: 3)
sourceWhere: Filter for source objects to classify
targetWhere: Filter for target objects to use as references
trainingSetWhere: Filter for training set (knn)

Returns the classification task status.

{
  "type": "object",
  "required": [
    "className",
    "classifyProperties",
    "basedOnProperties"
  ],
  "properties": {
    "k": {
      "type": "integer",
      "minimum": 1,
      "description": "Number of neighbors for knn"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "className": {
      "type": "string",
      "description": "Class to classify"
    },
    "basedOnProperties": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Properties to base classification on"
    },
    "classifyProperties": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Reference properties to classify"
    }
  }
}

weaviate_get_classification

Get the status of a classification task.

Args:

id: Classification task ID

Returns the classification status and results.

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Classification task ID"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    }
  }
}

weaviate_get_meta

Get Weaviate server metadata including version and modules.

Returns server information including hostname, version, and configured modules.

{
  "type": "object",
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    }
  }
}

weaviate_is_live

Check if Weaviate is alive (liveness probe).

This is a simple health check that returns ok if the server is running.

{
  "type": "object",
  "properties": {}
}

weaviate_is_ready

Check if Weaviate is ready to accept requests (readiness probe).

This checks if the server is fully initialized and ready for queries.

{
  "type": "object",
  "properties": {}
}

weaviate_get_nodes

Get information about all nodes in the Weaviate cluster.

Returns status, version, and statistics for each node.

Args:

output: Output verbosity (minimal or verbose)

Returns list of nodes with their status.

{
  "type": "object",
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "output": {
      "enum": [
        "minimal",
        "verbose"
      ],
      "type": "string",
      "description": "Output verbosity"
    }
  }
}

weaviate_get_cluster_statistics

Get cluster-wide statistics.

Returns aggregate statistics across all nodes in the cluster.

{
  "type": "object",
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    }
  }
}

weaviate_list_objects

List objects from a Weaviate class with pagination.

Args:

className: Name of the class
limit: Number of objects to return (1-100, default: 20)
offset: Offset for pagination
include: Additional fields to include (vector, classification, featureProjection)
tenant: Tenant name for multi-tenant collections

Returns a paginated list of objects.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 20,
      "maximum": 100,
      "minimum": 1,
      "description": "Number of objects to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "description": "Offset for pagination"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name for multi-tenant collections"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_get_object

Get a single object by ID.

Args:

className: Name of the class
id: Object ID (UUID)
include: Additional fields to include (vector, classification, featureProjection)
tenant: Tenant name for multi-tenant collections

Returns the object with all its properties.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID)"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name for multi-tenant collections"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_create_object

Create a new object in a Weaviate class.

Args:

className: Name of the class
properties: Object properties as key-value pairs
id: Optional UUID for the object (auto-generated if not provided)
vector: Optional custom vector (required if class has no vectorizer)
tenant: Tenant name for multi-tenant collections

Returns the created object.

{
  "type": "object",
  "required": [
    "className",
    "properties"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID, auto-generated if not provided)"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name for multi-tenant collections"
    },
    "vector": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Custom vector"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "properties": {
      "type": "object",
      "description": "Object properties"
    }
  }
}

weaviate_update_object

Update an existing object (replaces all properties).

Args:

className: Name of the class
id: Object ID (UUID)
properties: New object properties (replaces all existing)
vector: Optional new vector
tenant: Tenant name for multi-tenant collections

Returns the updated object.

{
  "type": "object",
  "required": [
    "className",
    "id",
    "properties"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID)"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "vector": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "New vector"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "properties": {
      "type": "object",
      "description": "New object properties (replaces all)"
    }
  }
}

weaviate_patch_object

Partially update an object (only provided properties are updated).

Args:

className: Name of the class
id: Object ID (UUID)
properties: Properties to update (existing properties not included are preserved)
tenant: Tenant name for multi-tenant collections

Returns confirmation of update.

{
  "type": "object",
  "required": [
    "className",
    "id",
    "properties"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID)"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "properties": {
      "type": "object",
      "description": "Properties to update"
    }
  }
}

weaviate_delete_object

Delete an object by ID.

Args:

className: Name of the class
id: Object ID (UUID) to delete
tenant: Tenant name for multi-tenant collections

Returns confirmation of deletion.

{
  "type": "object",
  "required": [
    "className",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID) to delete"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_object_exists

Check if an object exists by ID (HEAD request).

Args:

className: Name of the class
id: Object ID (UUID) to check
tenant: Tenant name for multi-tenant collections

Returns whether the object exists.

{
  "type": "object",
  "required": [
    "className",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID (UUID) to check"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_add_reference

Add a cross-reference from one object to another.

Cross-references link objects together. The source object must have a reference property defined in its class schema.

Args:

className: Source class name
id: Source object ID
propertyName: Name of the reference property
targetClass: Target class name
targetId: Target object ID
tenant: Tenant name for multi-tenant collections

Returns confirmation of reference addition.

{
  "type": "object",
  "required": [
    "className",
    "id",
    "propertyName",
    "targetClass",
    "targetId"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Source object ID"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "targetId": {
      "type": "string",
      "description": "Target object ID"
    },
    "className": {
      "type": "string",
      "description": "Source class name"
    },
    "targetClass": {
      "type": "string",
      "description": "Target class name"
    },
    "propertyName": {
      "type": "string",
      "description": "Reference property name"
    }
  }
}

weaviate_update_references

Replace all references for a property with a new set.

This replaces ALL existing references on the property with the provided list.

Args:

className: Source class name
id: Source object ID
propertyName: Name of the reference property
targets: Array of target references with class and id
tenant: Tenant name for multi-tenant collections

Returns confirmation of reference update.

{
  "type": "object",
  "required": [
    "className",
    "id",
    "propertyName"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Source object ID"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "className": {
      "type": "string",
      "description": "Source class name"
    },
    "propertyName": {
      "type": "string",
      "description": "Reference property name"
    }
  }
}

weaviate_delete_reference

Delete a specific cross-reference from an object.

Args:

className: Source class name
id: Source object ID
propertyName: Name of the reference property
targetClass: Target class name
targetId: Target object ID to remove
tenant: Tenant name for multi-tenant collections

Returns confirmation of reference deletion.

{
  "type": "object",
  "required": [
    "className",
    "id",
    "propertyName",
    "targetClass",
    "targetId"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Source object ID"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "targetId": {
      "type": "string",
      "description": "Target object ID to remove"
    },
    "className": {
      "type": "string",
      "description": "Source class name"
    },
    "targetClass": {
      "type": "string",
      "description": "Target class name"
    },
    "propertyName": {
      "type": "string",
      "description": "Reference property name"
    }
  }
}

weaviate_get_schema

Get the full Weaviate schema with all collections/classes.

Returns the complete schema including all classes, their properties, vectorizers, and configurations.

{
  "type": "object",
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string",
      "default": "json",
      "description": "Response format"
    }
  }
}

weaviate_get_class

Get a specific class/collection from the schema.

Args:

className: The name of the class to retrieve

Returns the class configuration including properties, vectorizer, and module config.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "className": {
      "type": "string",
      "description": "Name of the class to retrieve"
    }
  }
}

weaviate_create_class

Create a new class/collection in Weaviate.

Args:

className: Name of the class (must start with uppercase)
description: Description of the class
vectorizer: Vectorizer module (text2vec-openai, text2vec-cohere, text2vec-huggingface, none)
properties: Array of property definitions
moduleConfig: Module-specific configuration
vectorIndexType: Type of vector index (hnsw, flat)
multiTenancyEnabled: Enable multi-tenancy for this class

Returns the created class configuration.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class (must start with uppercase)"
    },
    "description": {
      "type": "string",
      "description": "Description of the class"
    },
    "moduleConfig": {
      "type": "object",
      "description": "Module-specific configuration"
    },
    "vectorIndexType": {
      "enum": [
        "hnsw",
        "flat"
      ],
      "type": "string",
      "description": "Vector index type"
    },
    "replicationFactor": {
      "type": "number",
      "description": "Replication factor"
    },
    "multiTenancyEnabled": {
      "type": "boolean",
      "description": "Enable multi-tenancy"
    }
  }
}

weaviate_update_class

Update an existing class/collection configuration.

Note: Not all properties can be updated after creation. Typically you can update:

description
invertedIndexConfig
replicationConfig
vectorIndexConfig (some settings)

Args:

className: Name of the class to update
description: New description
invertedIndexConfig: Inverted index configuration
replicationConfig: Replication configuration

Returns the updated class configuration.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class to update"
    },
    "description": {
      "type": "string",
      "description": "New description"
    },
    "replicationFactor": {
      "type": "number",
      "description": "New replication factor"
    }
  }
}

weaviate_delete_class

Delete a class/collection and all its data.

WARNING: This permanently deletes the class and all objects in it.

Args:

className: Name of the class to delete

Returns confirmation of deletion.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class to delete"
    }
  }
}

weaviate_add_property

Add a new property to an existing class.

Args:

className: Name of the class
name: Property name
dataType: Array of data types (e.g., ["text"], ["int"], ["boolean"])
description: Property description
indexFilterable: Enable filtering on this property
indexSearchable: Enable full-text search
tokenization: Tokenization method (word, lowercase, whitespace, field)

Returns confirmation of property addition.

{
  "type": "object",
  "required": [
    "className",
    "name",
    "dataType"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Property name"
    },
    "dataType": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Data types (e.g., [\"text\"], [\"int\"])"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "description": {
      "type": "string",
      "description": "Property description"
    },
    "indexFilterable": {
      "type": "boolean",
      "description": "Enable filtering"
    },
    "indexSearchable": {
      "type": "boolean",
      "description": "Enable full-text search"
    }
  }
}

weaviate_graphql

Execute a raw GraphQL query against Weaviate.

Use this for complex queries not covered by other search tools.

Args:

query: The GraphQL query string

Returns the GraphQL response.

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "GraphQL query string"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    }
  }
}

weaviate_near_vector

Search for objects similar to a given vector.

Args:

className: Name of the class to search
vector: The query vector (array of numbers)
limit: Maximum number of results (default: 10)
certainty: Minimum certainty threshold (0-1)
distance: Maximum distance threshold
fields: Fields to return (default: _additional { id distance certainty })
where: Optional filter
tenant: Tenant name for multi-tenant collections

Returns matching objects sorted by similarity.

{
  "type": "object",
  "required": [
    "className",
    "vector"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results"
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Fields to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "vector": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Query vector"
    },
    "distance": {
      "type": "number",
      "description": "Maximum distance"
    },
    "certainty": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Minimum certainty (0-1)"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_near_text

Search for objects semantically similar to text concepts.

Requires a text vectorizer module (text2vec-openai, text2vec-cohere, etc.)

Args:

className: Name of the class to search
concepts: Array of text concepts to search for
limit: Maximum number of results (default: 10)
certainty: Minimum certainty threshold (0-1)
distance: Maximum distance threshold
moveTo: Move results towards these concepts (optional)
moveAwayFrom: Move results away from these concepts (optional)
fields: Fields to return
where: Optional filter
tenant: Tenant name for multi-tenant collections

Returns matching objects sorted by semantic similarity.

{
  "type": "object",
  "required": [
    "className",
    "concepts"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results"
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Fields to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "concepts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Text concepts to search for"
    },
    "distance": {
      "type": "number",
      "description": "Maximum distance"
    },
    "certainty": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Minimum certainty (0-1)"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_near_object

Search for objects similar to an existing object by ID.

Args:

className: Name of the class to search
id: Object ID to find similar objects to
limit: Maximum number of results (default: 10)
certainty: Minimum certainty threshold (0-1)
distance: Maximum distance threshold
fields: Fields to return
where: Optional filter
tenant: Tenant name for multi-tenant collections

Returns matching objects sorted by similarity.

{
  "type": "object",
  "required": [
    "className",
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Object ID to find similar objects to"
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results"
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Fields to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "distance": {
      "type": "number",
      "description": "Maximum distance"
    },
    "certainty": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Minimum certainty (0-1)"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_hybrid

Perform hybrid search combining vector search with keyword search (BM25).

Args:

className: Name of the class to search
query: The search query text
alpha: Balance between vector (1) and keyword (0) search (default: 0.5)
vector: Optional custom vector (if not using text vectorizer)
properties: Properties to search in for BM25
fusionType: How to fuse results (rankedFusion or relativeScoreFusion)
limit: Maximum number of results (default: 10)
fields: Fields to return
where: Optional filter
tenant: Tenant name for multi-tenant collections

Returns matching objects combining both search methods.

{
  "type": "object",
  "required": [
    "className",
    "query"
  ],
  "properties": {
    "alpha": {
      "type": "number",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "description": "Vector (1) vs keyword (0) balance"
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results"
    },
    "query": {
      "type": "string",
      "description": "Search query text"
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Fields to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "vector": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Custom query vector"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "properties": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Properties to search for BM25"
    }
  }
}

weaviate_bm25

Perform BM25 keyword search (no vector search).

Args:

className: Name of the class to search
query: The search query text
properties: Properties to search in
limit: Maximum number of results (default: 10)
fields: Fields to return
where: Optional filter
tenant: Tenant name for multi-tenant collections

Returns matching objects based on keyword relevance.

{
  "type": "object",
  "required": [
    "className",
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum results"
    },
    "query": {
      "type": "string",
      "description": "Search query text"
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Fields to return"
    },
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "tenant": {
      "type": "string",
      "description": "Tenant name"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "properties": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Properties to search in"
    }
  }
}

weaviate_get_tenants

List all tenants for a multi-tenant class.

Args:

className: Name of the multi-tenant class

Returns list of tenants with their activity status.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "format": {
      "enum": [
        "json",
        "markdown"
      ],
      "type": "string"
    },
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_create_tenants

Create one or more tenants for a multi-tenant class.

The class must have multi-tenancy enabled.

Args:

className: Name of the multi-tenant class
tenants: Array of tenant definitions with name and optional activityStatus

Returns the created tenants.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_update_tenants

Update tenant activity status for a multi-tenant class.

Use this to activate (HOT/ACTIVE), deactivate (COLD/INACTIVE), freeze (FROZEN), or offload (OFFLOADED) tenants.

Args:

className: Name of the multi-tenant class
tenants: Array of tenant updates with name and activityStatus

Returns confirmation of update.

{
  "type": "object",
  "required": [
    "className"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    }
  }
}

weaviate_delete_tenants

Delete tenants from a multi-tenant class.

WARNING: This permanently deletes the tenants and all their data.

Args:

className: Name of the multi-tenant class
tenantNames: Array of tenant names to delete

Returns confirmation of deletion.

{
  "type": "object",
  "required": [
    "className",
    "tenantNames"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "tenantNames": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tenant names to delete"
    }
  }
}

weaviate_tenant_exists

Check if a tenant exists in a multi-tenant class.

Args:

className: Name of the multi-tenant class
tenantName: Tenant name to check

Returns whether the tenant exists.

{
  "type": "object",
  "required": [
    "className",
    "tenantName"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "tenantName": {
      "type": "string",
      "description": "Tenant name to check"
    }
  }
}

weaviate_activate_tenants

Activate (warm up) tenants to make them available for queries.

This is a convenience method that sets tenant status to ACTIVE.

Args:

className: Name of the multi-tenant class
tenantNames: Array of tenant names to activate

Returns confirmation of activation.

{
  "type": "object",
  "required": [
    "className",
    "tenantNames"
  ],
  "properties": {
    "className": {
      "type": "string",
      "description": "Name of the class"
    },
    "tenantNames": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tenant names to activate"
    }
  }
}