Database

ClickHouse documents a fully managed remote Model Context Protocol server for ClickHouse Cloud at clickhouse.com/docs/cloud/features/ai-ml/remote-mcp. Connect MCP clients to the HTTP endpoint `https://mcp.clickhouse.cloud/mcp` with OAuth 2.0 (browser sign-in with ClickHouse Cloud credentials; no separate API key required per docs). Agents can list databases and tables, inspect schemas, and run scoped read-only SELECT queries; the remote server also exposes richer ClickHouse Cloud integration such as service management, backup monitoring, ClickPipe visibility, and billing data per ClickHouse docs. Enable per service in the Cloud console (Connect → MCP). For self-hosted ClickHouse, ClickHouse maintains the separate open-source mcp-clickhouse project—distinct from this Cloud remote MCP.

Google Cloud documents a remote BigQuery Model Context Protocol server at docs.cloud.google.com/bigquery/docs/use-bigquery-mcp, enabled when the BigQuery API is enabled. Connect MCP clients to the managed HTTP endpoint `https://bigquery.googleapis.com/mcp` with OAuth 2.0 and IAM (API keys are not accepted). Documented IAM roles include MCP Tool User (`roles/mcp.toolUser`), BigQuery Job User (`roles/bigquery.jobUser`), and BigQuery Data Viewer (`roles/bigquery.dataViewer`). Tools include `execute_sql` and `execute_sql_readonly` per the use guide; `execute_sql_readonly` allows only read-only operations while `execute_sql` is the sole non-read-only tool. Limitations documented: query processing capped at three minutes by default, results limited to 3,000 rows, and Google Drive external tables unsupported for those SQL tools.

LanceDB maintains a reference Model Context Protocol server in the lancedb/lancedb-mcp-server repository (linked from lancedb/lancedb issue #2341), implemented with FastMCP and LanceDB embeddings. Tools include `ingest_docs` (embed and store documents), `query_table` (semantic retrieval with configurable top_k and query_type), and `table_details` (schema and row counts) per the README. Configuration uses `uv run lancedb_mcp.py` with environment variables `LANCEDB_URI` (default `~/lancedb`), `TABLE_NAME`, `EMBEDDING_FUNCTION` (default sentence-transformers), and `MODEL_NAME` (default all-MiniLM-L6-v2). The repo describes itself as a basic serverless MCP reference for building more complex LanceDB agent apps—not a full production managed endpoint.

MotherDuck documents a remote Model Context Protocol server at motherduck.com/docs/sql-reference/mcp hosted at `https://api.motherduck.com/mcp` with OAuth (or Bearer token) and read-write SQL access to MotherDuck cloud databases. Tools include `list_databases`, `list_tables`, `list_columns`, `search_catalog`, `query`, `query_rw`, `ask_docs_question`, Dive tools (`list_dives`, `read_dive`, `view_dive`, `save_dive`, etc.), and Flight scheduling tools (`list_flights`, `create_flight`, `run_flight`, etc.) per MotherDuck MCP docs. For local DuckDB files or custom configs, MotherDuck points to the open-source `mcp-server-motherduck` package (`uvx mcp-server-motherduck --db-path md:`) on github.com/motherduckdb/mcp-server-motherduck.

Weaviate documents a built-in Model Context Protocol server in the main `weaviate/weaviate` binary from v1.37.1 onward at docs.weaviate.io/weaviate/mcp/mcp-server, exposed as a Streamable HTTP endpoint at `/v1/mcp` on the same port as the REST API (default 8080). Enable with `MCP_SERVER_ENABLED=true`; optional `MCP_SERVER_WRITE_ACCESS_ENABLED=true` registers `weaviate-objects-upsert`. Tools include `weaviate-collections-get-config`, `weaviate-tenants-list`, `weaviate-query-hybrid`, and `weaviate-objects-upsert` (write-gated). Authentication uses existing API keys/Bearer tokens with RBAC permissions `read_mcp`, `create_mcp`, and `update_mcp` per Weaviate 1.37 release notes. The standalone weaviate/mcp-server-weaviate repository is deprecated in favor of this built-in server.

Chroma documents an official Model Context Protocol server in the chroma-core/chroma-mcp repository and docs.trychroma.com/integrations/frameworks/anthropic-mcp, started with `uvx chroma-mcp` over stdio. Tools include `chroma_list_collections`, `chroma_create_collection`, `chroma_peek_collection`, `chroma_modify_collection`, `chroma_delete_collection`, `chroma_add_documents`, `chroma_query_documents`, `chroma_get_documents`, `chroma_update_documents`, and `chroma_delete_documents` per the README. Client types documented: ephemeral (default), persistent (`--client-type persistent --data-dir`), HTTP self-hosted, and Chroma Cloud (`--client-type cloud` with API keys). Embedding function options include default, Cohere, OpenAI, Jina, VoyageAI, and Roboflow per Chroma MCP docs.

PlanetScale documents a hosted Model Context Protocol server at planetscale.com/docs/connect/mcp, reachable at `https://mcp.pscale.dev/mcp/planetscale` with OAuth authentication for organizations, databases, branches, schemas, and Insights data. An insights-only endpoint at `https://mcp.pscale.dev/mcp/planetscale-insights-only` omits read/write query tools. Tools documented include organization/database/branch listing, schema inspection, `planetscale_get_insights`, documentation search, and—when scopes allow—`planetscale_execute_read_query` and `planetscale_execute_write_query` with replica routing, ephemeral credentials, and destructive-query safeguards per the January 2026 changelog. PlanetScale notes the older local CLI MCP path is deprecated in favor of the hosted HTTP server for Cursor, Claude Code, and other MCP clients.

Turso documents a built-in Model Context Protocol server in the Turso CLI (`tursodb`) at docs.turso.tech/cli/mcp-server, started with `tursodb /path/to/database.db --mcp` over stdio JSON-RPC. Tools include `open_database`, `current_database`, `list_tables`, `describe_table`, `execute_query` (SELECT-only), `insert_data`, `update_data`, `delete_data`, and `schema_change` (CREATE/ALTER/DROP) per the Mintlify MCP reference. Turso's launch blog at turso.tech/blog/introducing-the-turso-database-mcp-server shows Claude Desktop and Claude Code configuration via `claude mcp add` with the same `--mcp` flag—no separate npm package required for local embedded databases.

Upstash documents an official Model Context Protocol server at upstash.com/docs/agent-resources/mcp implemented in the `upstash/mcp-server` repository and npm package `@upstash/mcp-server`. Started with `npx -y @upstash/mcp-server@latest --email YOUR_EMAIL --api-key YOUR_API_KEY`, it exposes tools for serverless Redis, QStash, Workflow runs, and Upstash Box so agents can manage and debug account resources from Cursor, Claude Code, VS Code, Codex, and other MCP clients. Read-only API keys automatically disable mutating tools per docs; optional `--transport http`, `--disable-telemetry`, and Upstash Box API key flags are documented for advanced setups.

Convex documents a Model Context Protocol server shipped in the Convex CLI at docs.convex.dev/ai/convex-mcp-server, started locally with `npx -y convex@latest mcp start` over stdio after linking a project via `npx convex dev`. Tools include `status` (deployment selector), `tables` (declared and inferred schemas), `data` (paginated documents), `runOneoffQuery` (sandboxed read-only JS), `functionSpec`, `run` (invoke deployed functions), `logs`, `insights` (72-hour OCC and resource-limit health), and `envList`/`envGet`/`envSet`/`envRemove`. Flags such as `--prod`, `--preview-name`, `--deployment-name`, and `--disable-tools` restrict scope; production writes require `--dangerously-enable-production-deployments` per changelog defaults.

MotherDuck documents a remote Model Context Protocol server at `https://api.motherduck.com/mcp` (fully managed, read-write) that lets Claude, ChatGPT, Cursor, Claude Code, Codex, and other MCP clients query MotherDuck cloud databases via OAuth or Bearer tokens with zero local install per motherduck.com/docs/sql-reference/mcp. Remote tools include read-only `query` and read-write `query_rw` plus schema exploration helpers documented in the MCP workflows guide. For local DuckDB files, S3 paths, or custom limits, the open-source `mcp-server-motherduck` package (motherduckdb/mcp-server-motherduck on GitHub, PyPI `mcp-server-motherduck`) runs via `uvx` with flags such as `--db-path`, `--motherduck-token`, and `--read-write` for self-hosted stdio or HTTP transports.

The zilliztech/mcp-server-milvus project (documented at milvus.io/docs/milvus_and_mcp.md) exposes Milvus vector-database operations to MCP clients such as Claude Desktop and Cursor. The recommended launch path is `uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530` without a separate install step, with optional `MILVUS_URI`, `MILVUS_TOKEN`, and `MILVUS_DB` environment variables. Tools listed in Milvus docs include `milvus-text-search`, `milvus-hybrid-search`, `milvus-multi-vector-search`, `milvus-query`, and `milvus-count` for collection management, semantic retrieval, filtered hybrid search, and entity counts.

The open-source ClickHouse MCP server (PyPI package `mcp-clickhouse`, repository ClickHouse/mcp-clickhouse) exposes MCP tools such as `run_query`, `list_databases`, and paginated `list_tables` against ClickHouse clusters, defaulting to read-only SQL unless `CLICKHOUSE_ALLOW_WRITE_ACCESS` is enabled. Optional chDB extras add `run_chdb_select_query` for embedded queries over files and URLs. HTTP/SSE transports require authentication via `CLICKHOUSE_MCP_AUTH_TOKEN`, FastMCP OAuth/OIDC providers, or explicit `CLICKHOUSE_MCP_AUTH_DISABLED=true` for local dev; a `/health` endpoint supports orchestrator probes without credentials per README guidance.

Snowflake documents a Snowflake-hosted Model Context Protocol (MCP) endpoint that fronts governed Snowflake data and Cortex workloads without provisioning a separate MCP bridge VM. Administrators declare tools with SQL (`CREATE MCP SERVER`)—for example Cortex Search queries, Cortex Analyst chat-style messages, Cortex Agent executions, parameterized SQL runners, or custom tools backed by Snowflake-native functions—and clients authenticate using Snowflake OAuth against the MCP revision pinned in Snowflake release notes.

The DuckDB-distributed community extension `duckdb_mcp` embeds MCP client and server capabilities directly inside DuckDB. Installers load it via `INSTALL duckdb_mcp FROM community` followed by `LOAD duckdb_mcp`, after which SQL can attach remote MCP servers (stdio/TCP/WebSocket transports), enumerate resources (`mcp_list_resources`), invoke remote tools (`mcp_call_tool`), and wrap responses with `read_csv`/`read_json`/`read_parquet` URIs routed through `mcp://`. In reverse direction, DuckDB can publish tables, queries, and execution-bound tools (`mcp_publish_table`, `mcp_publish_query`, `mcp_publish_execution_tool`) while `mcp_server_start` exposes them to external MCP-compatible clients.

Official Neon MCP integration exposes Neon Postgres projects to MCP-capable assistants via Streamable HTTP (`https://mcp.neon.tech/mcp`), legacy SSE (`https://mcp.neon.tech/sse`), or a locally launched `@neondatabase/mcp-server-neon` package. Documentation lists tools for project and branch lifecycle, SQL execution, migration rehearsal branches, slow-query diagnostics, Neon Auth provisioning, Data API setup, and embedded Neon docs retrieval—each mapped to Neon API operations.

Official Qdrant MCP server implementation that gives AI agents a semantic memory layer backed by Qdrant vector search. It exposes MCP tools for storing information and retrieving relevant context, so assistants can persist and recall facts across sessions instead of relying only on short chat history.

Provides AI agents access to Prisma schemas, migration planning, and database introspection capabilities. Agents can propose migrations, explore data models, and generate type-safe queries based on your Prisma setup. Works with local projects and remote Prisma Data Proxy deployments.

Allows AI agents to run queries, inspect collections, execute aggregation pipelines, and analyze explain plans against MongoDB clusters. Debug document models and performance issues by having the agent explore data structures directly. Supports MongoDB Atlas federated queries and Atlas Search.

Enables AI agents to inspect Pinecone vector database indexes, query vectors, manage collections, and debug retrieval behavior. Useful for teams using vector search in RAG applications who want to understand index statistics and optimize similarity search performance.

Exposes Redis key-value store operations to AI agents including GET/SET, list operations, hash manipulation, and pub/sub debugging. Agents can inspect caches, debug session stores, and check feature flags without dumping entire databases. Supports Redis Cluster and Sentinel configurations.

Connects agents to Supabase projects for table inspection, Edge Function debugging, database triggers, and real-time subscriptions. Agents can inspect RLS policies, view logs, and manage database types without the Supabase dashboard. Supports both hosted and self-hosted Supabase instances.

Enables AI agents to execute read-only SQL queries against PostgreSQL databases, inspect table schemas, and analyze query performance. Agents can debug data issues or prepare analytics without requiring direct database credentials in the conversation. Supports connection pooling and multiple database targets.

Provides lightweight SQL access to local SQLite database files for quick analytics, schema inspection, and prototyping without database server overhead. Agents can query, analyze, and generate reports from embedded datasets. Ideal for app sandboxes, development databases, and data exploration.

pg-mcp-server is a Model Context Protocol server implementation that connects AI agents to PostgreSQL databases. It registers database schemas as MCP resource templates and exposes SQL execution as an MCP tool. Agents can introspect table structures, run parameterized queries, and manage transactions without leaving the chat interface. Designed as a reference implementation for database MCP integrations.