MCP-серверы

Apache Doris' MCP server provides agents with governed access to Doris analytics databases for schema discovery, query assistance, and operational investigation.

Apache IoTDB's MCP server connects agents to time-series data and metadata for operational analysis, industrial telemetry exploration, and query assistance.

Apache Solr's MCP server connects agents to search collections and query workflows for schema discovery, relevance investigation, and search application development.

Fivetran's MCP server helps agents inspect data connectors and sync health, diagnose broken connections, and answer operational questions about managed ELT pipelines.

InfluxData's MCP server connects agents to InfluxDB 3 for SQL queries, schema exploration, and time-series database operations.

Google's MCP Toolbox provides secure, ready-made and custom tools for database queries, schema operations, and semantic search in agent workflows.

DataStax's official MCP server for Astra DB, a serverless database built on Apache Cassandra with native vector search. Lets AI agents create and manage collections, insert and update records, and run similarity and metadata queries, making it a convenient backend for retrieval-augmented generation and agent memory workloads.

Community-supported MCP server from the Couchbase ecosystem that lets AI assistants interact with data in Couchbase clusters and Capella. Exposes tools to browse scopes and collections, run SQL++ (N1QL) queries, and read or modify documents, with authentication and safety controls enforced by the server. Useful for conversational data exploration and operational queries against Couchbase.

Official MCP server for Meilisearch, the open-source, lightning-fast search engine. Enables MCP-compatible clients to manage search indexes, add and update documents, run searches, and adjust index settings through natural language. Useful for building and debugging search experiences and for letting agents query application data stored in Meilisearch.

Official MCP server for DuckDB and MotherDuck. Lets AI assistants run SQL analytics directly against local DuckDB files, in-memory databases, S3-hosted data, and MotherDuck cloud warehouses. Supports read and write queries, browsing database catalogs, and switching between connections on the fly, making it well suited for conversational data exploration and lightweight analytics.

Prisma's official MCP server that lets AI tools manage Prisma ORM projects and Prisma Postgres databases through natural language. Provides both a local server for working with a project's Prisma schema and migrations, and a remote server for provisioning and managing Prisma Postgres databases. Useful for scaffolding models, generating and applying migrations, and running database workflows from an AI coding assistant.

MCP server for interacting with a Tinybird Workspace from any MCP client. Lets AI agents explore data sources, call published API endpoints, run SQL queries over real-time data, and push datafiles, making Tinybird's analytics readily available to LLM-driven workflows.

MCP server for the Databricks Data Intelligence Platform. Enables AI agents to run SQL against the Unity Catalog, inspect schemas and tables, and manage and monitor jobs, bringing lakehouse data and workflows into AI-powered development tools.

Official dbt Labs MCP server for analytics engineering workflows. Lets AI agents run dbt commands (build, run, test), inspect models and lineage via the dbt project, and query the Semantic Layer and Discovery API in dbt Cloud. Useful for transforming data, validating models, and answering metric questions grounded in governed definitions.

MCP server for DuckDB, the fast in-process analytical database. Lets AI agents run analytical SQL over local files (CSV, Parquet, JSON), attach databases, inspect schemas, and profile queries. Ideal for ad-hoc data analysis, ETL prototyping, and querying large columnar files without a separate database server.

Official MCP server for the Milvus vector database. Lets AI agents create collections, insert vectors, and run similarity and scalar-filtered searches over large-scale embedding data, enabling retrieval and long-term memory for AI applications.

Official MCP server for the Neo4j graph database. Enables AI agents to run Cypher queries, inspect graph schemas, and manage nodes and relationships. Includes support for natural-language to Cypher translation and graph-backed memory for agents. Useful for knowledge graphs, recommendations, fraud detection, and relationship-heavy data.

MCP server for the Weaviate open-source vector database. Enables AI agents to store objects, run semantic and hybrid searches, and manage collections, making it a memory and retrieval backend for RAG applications directly from AI-powered tools.

MCP server for MySQL and MariaDB that lets AI agents inspect schemas, list tables, and run parameterized SQL queries. Supports read-only or read-write modes so agents can explore data, debug, and prototype against a MySQL database with controlled access.

MCP server for Airtable that lets AI agents read and write records, list bases and tables, inspect field schemas, and run filtered queries. Ideal for turning Airtable into a lightweight backend or knowledge base that agents can manage conversationally.

MCP server for Google BigQuery that lets AI agents explore datasets, inspect table schemas, and run SQL analytics queries with dry-run cost estimation. Useful for natural-language data analysis, ad-hoc reporting, and pipeline debugging against large-scale BigQuery warehouses.