For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.mcpbundles.com/bundle/weaviate
Skill page: https://www.mcpbundles.com/skills/weaviate
Tools: 31
Live probe refreshed Nov 11, 2026 · Endpoint host mcp.mcpbundles.com
AI Skill
SKILL.md
Domain knowledge for Weaviate — workflow patterns, data models, and gotchas for your AI agent.
Weaviate
Weaviate is an open-source vector database for AI-native applications. Store and query embeddings, perform similarity search, build recommendation systems.
Data Model
Collections — schema-defined buckets; inventory them and retire unused ones.
Objects & retrieval — CRUD plus semantic and hybrid (keyword + vector) queries; point reads need collection + id.
Schema graph — detailed class definitions, cross-references, and property usage stats.
Analysis — collection profiling, distribution studies across properties and vectors.
Two credential field setups
Setup
Fields
Routing
Weaviate Cloud or remote cluster
instance URL + API key
Direct HTTPS/gRPC
Local Weaviate on this machine
API key + HTTP/gRPC ports (+ desktop tunnel)
MCPBundles Desktop to localhost
Operational order (unfamiliar cluster)
List collections — inventory collection names before any scoped call.
Inspect one collection — read detailed schema (properties, vectorizer, cross-references).
List objects, search, or hybrid search — pass collection on every call unless you saved a default on the credential.
Gotchas
Cluster setup: Each credential binds to one Weaviate deployment. Set default_collection on the credential when one collection is used repeatedly; otherwise list collections and pass the name on each call.
Instance URL: Use the full Weaviate Cloud hostname (https://….weaviate.cloud). Host-only URLs work but the scheme helps validation surface clearer errors.
Localhost: Use the Local Weaviate on this computer setup — not a public URL field with localhost in it.
Vectorization: Collections with text2vec-openai need the optional OpenAI API key on the credential.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms
Weaviate
Add to your AI client, then sign in once when you connect.
Weaviate is an open-source vector database designed for AI-native applications and semantic search. Store and query vector embeddings, perform similarity searches, integrate with ML models, build recommendation systems, and enable semantic search capabilities for AI-powered applications.
This listing identifies a third-party integration. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
Universal fetch tool that retrieves any object, schema, or metadata using smart ID routing with colon-separated format. Supports direct object retrieval, schema inspection, and collection metadata.
Fetch — Universal fetch tool that retrieves any object, schema, or metadata using smart ID routing with colon-separated format. Supports direct object retrieval, schema inspection, and collection metadata.
Search — Search Weaviate vector store using hybrid semantic + keyword search or BM25. Returns ranked results with IDs, titles, and scores.
Weaviate Analyze Property Distribution — Analyze distribution of values for a specific property. Shows top values, uniqueness, null rate, and statistics. Essential for understanding data patterns and quality.
Weaviate Analyze Vector Distribution — Analyze vector embeddings distribution. Shows dimensionality, magnitude statistics, density, and similarity patterns. Critical for understanding embedding quality.
Weaviate Backup Collection — Create a complete backup of a collection including schema and data.
Weaviate Batch Delete — Delete multiple objects matching a filter condition. DESTRUCTIVE operation with safety limits. Requires explicit confirmation and WHERE filter to prevent accidental mass deletion.
Weaviate Batch Import — Import multiple objects in batch. Optimized for bulk loading with automatic error handling, retry logic, and progress reporting. Much faster than individual inserts.
Weaviate Batch Update — Update multiple objects matching a filter condition. Useful for bulk status changes, migrations, or data corrections. Includes safety limits to prevent accidental mass updates.
Weaviate Check Orphaned References — Check for broken cross-references in collections. Returns objects with references to deleted or non-existent objects.
Frequently Asked Questions
What is the Weaviate MCP server?
Weaviate is an open-source vector database designed for AI-native applications and semantic search. Store and query vector embeddings, perform similarity searches, integrate with ML models, build recommendation systems, and enable semantic search capabilities for AI-powered applications. It provides 31 tools that AI agents can use through the Model Context Protocol (MCP).
How do I connect Weaviate to my AI agent?
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/weaviate. Authentication is handled automatically.
Standard connector25 free calls every 30 days, then from $19/month
$19 / month
Subject to fair usage limits
Weaviate Check Vector Quality — Check vector quality for corruption issues. Detects zero vectors, NaN values, and vectors with abnormal magnitude. Critical for maintaining search quality.
Weaviate Compare Collections — Compare two collections to find differences in schemas, object counts, and configurations. Useful for validating migrations or understanding related collections.
Weaviate Copy Objects — Copy objects between collections. Useful for data migration, creating backups, or duplicating data for testing. Optionally preserves or regenerates vectors.
Weaviate Create Collection — Create a new Weaviate collection with custom schema. Define properties, data types, and optionally configure a vectorizer for automatic embedding generation.
Weaviate Data Quality Report — Generate detailed data quality report. Combines vector quality, property completeness, duplicates, and collection health into a single report with actionable recommendations.
Weaviate Delete — Delete object(s) or entire collection from Weaviate. Supports three modes: single object deletion, bulk deletion with failure tracking, and collection removal. All deletions are permanent and cannot be undone.
Weaviate Export Collection — Export collection data including vectors, properties, and metadata for backup or migration.
Weaviate Find Duplicates — Find near-duplicate objects using vector similarity. Helps identify redundant data and potential data quality issues from duplicate imports.
Weaviate Find Missing Vectors — Find objects without vector embeddings. Critical for debugging semantic search issues - objects without vectors won't appear in similarity searches.
Weaviate Find Unused Collections — Find collections that have no objects (empty collections). Useful for identifying collections that can be safely removed or need to be populated.
Weaviate Get Cross References — Analyze cross-reference relationships between collections. Shows which collections reference which other collections, similar to foreign key relationships.
Weaviate Get Property Usage — Analyze property usage in a collection. Shows which properties are consistently populated vs frequently null/empty. Useful for understanding data completeness and identifying unused schema fields.
Weaviate Get Reference Graph — Get a graph of cross-references between collections. Shows which collections reference each other and how.
Weaviate Get Schema Detailed — Get full schema information for a collection including properties, data types, vectorizer configuration, indexes, and module settings.
Weaviate List Collections — List all Weaviate collections with rich filtering options. Supports pattern matching, schema inclusion, object counts, and pagination. Use this for collection discovery and understanding your data structure.
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does Weaviate provide?
Weaviate provides 31 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
What authentication does Weaviate require?
Weaviate uses API Key. Weaviate requires credentials. Connect via MCPBundles and authentication is handled automatically.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.
More in developer tools
Other MCP servers in this category from the directory index