MCP servers that inspect database schemas
List tables, describe columns, and explore schema so the AI writes correct queries.
38 servers · Last updated August 1, 2026
TL;DR: Before an agent can query well, it needs to see the schema. These servers list tables, describe columns and types, and surface relationships — the context that turns vague prompts into correct SQL. Pair one with an execute-SQL server for an end-to-end data agent.
Bottom line: if you only try one, InstantDB MCP is the most popular option for this (10,343★). 37 more compared below.
Compare 38 servers
| Server | Transport | Auth | Verified | Stars | Tools for this |
|---|---|---|---|---|---|
| InstantDB MCP | Remote (HTTP) | OAuth | — | 10,343 | get-schema, push-schema |
| Vizro-MCP | Local (stdio) | No auth | — | 3,703 | get_model_json_schema |
| Postgres MCP Pro | Local (stdio) | API key | 2,900 | list_schemas, list_objects | |
| Supabase MCP Server | Remote (HTTP) | OAuth | 2,700 | list_tables | |
| Neon MCP Server | Remote (HTTP) | OAuth | 2,100 | list_projects / describe_project / create_project / delete_project, create_branch / delete_branch / describe_branch / reset_from_parent, get_database_tables / describe_table_schema +1 | |
| Anyquery | Local (stdio) | No auth | — | 1,726 | describeTable |
| MongoDB MCP Server | Local (stdio) | API key | 1,500 | collection-schema | |
| MySQL MCP Server | Local (stdio) | No auth | — | 1,304 | get_schema_info |
| Neo4j Cypher MCP Server | Local (stdio) | API key | 1,300 | get_neo4j_schema | |
| ClickHouse MCP Server | Local (stdio) | API key | 1,000 | list_databases, list_tables | |
| Query | Supabase MCP Server | Local (stdio) | API key | — | 826 | get_schemas, get_table_schema |
| MotherDuck / DuckDB MCP Server | Local (stdio) | API key | 800 | list_databases, list_tables | |
| Chroma MCP Server | Local (stdio) | API key | 600 | chroma_list_collections | |
| Pinecone Developer MCP Server | Local (stdio) | API key | 500 | describe-index, describe-index-stats | |
| Airtable MCP Server | Local (stdio) | API key | — | 449 | list_tables, describe_table |
| MCP Alchemy | Local (stdio) | No auth | — | 410 | schema_definitions |
| Multi Database MCP Server | Local (stdio) | No auth | — | 392 | schema_<db_id>, generate_schema_<db_id> |
| Bagel | Remote (SSE) | No auth | — | 383 | describe_data_source, describe_topic |
| Graphlit MCP Server | Local (stdio) | API key | — | 375 | Visually Describe Image |
| Apache Doris MCP Server | Local (stdio) | No auth | — | 306 | get_table_schema |
| Firebase MCP | Local (stdio) | API key | — | 245 | firestore_list_collections |
| Milvus MCP Server | Local (stdio) | API key | — | 233 | milvus_list_collections |
| MongoDB Lens | Local (stdio) | No auth | — | 204 | analyze-schema, compare-schemas, generate-schema-validator |
| Snowflake MCP Server | Local (stdio) | API key | — | 183 | list_databases, list_schemas, list_tables +1 |
| MySQL MCP Server | Local (stdio) | No auth | — | 162 | list_tables, describe_table |
| Confluent MCP Server | Local (stdio) | API key | — | 160 | describe-configured-connection, describe-consumer-group, describe-flink-table +3 |
| BigQuery MCP server | Local (stdio) | No auth | — | 127 | describe-table |
| MCP SQLite Server | Local (stdio) | No auth | — | 110 | list_tables, get_table_schema |
| Trino MCP Server | Local (stdio) | OAuth | — | 109 | list_schemas, list_tables, get_table_schema |
| SQLite Explorer MCP Server | Local (stdio) | No auth | — | 105 | list_tables, describe_table |
| Prisma MCP | Local (stdio) | OAuth | — | 43 | IntrospectSchemaTool |
| Hologres MCP Server | Local (stdio) | API key | — | 34 | list_hg_schemas, list_hg_tables_in_a_schema |
| InfluxDB MCP Server | Local (stdio) | API key | — | 33 | get_measurement_schema, list_databases |
| Couchbase MCP Server | Local (stdio) | API key | — | 32 | get_schema_for_collection |
| Kafka Schema Registry MCP Server | Local (stdio) | OAuth | — | 31 | register_schema, count_schemas, count_schema_versions +6 |
| GreptimeDB MCP Server | Local (stdio) | No auth | — | 28 | describe_table |
| YDB MCP | Local (stdio) | API key | — | 27 | ydb_describe_path |
| Turso Cloud MCP Server | Local (stdio) | API key | — | 16 | list_databases, list_tables, describe_table |
The servers
Create, manage, and query your InstantDB apps, schemas, permissions, and data from your AI editor.
MCP server that works alongside an LLM to build validated Vizro charts and dashboards.
Read/write Postgres access plus index tuning, EXPLAIN plans, and database health analysis for AI agents.
Official Supabase server: manage tables, run SQL, branches, configs and edge functions from your AI client.
Manage serverless Postgres on Neon with natural language: projects, branches, migrations, and SQL.
Run SQL over files, databases, and 40+ apps (GitHub, Notion, Chrome, Todoist) — and expose them to LLMs via MCP.
Official MongoDB server connecting Atlas, Community, or Enterprise deployments to AI tools.
Secure, structured access to MySQL databases for AI clients — query, sample, and inspect schemas via MCP.
Run Cypher queries and explore graph schema on Neo4j from your AI assistant.
Official ClickHouse server: read-only SQL queries plus database/table exploration and chDB support.
Safely run SQL, manage schema, call the Supabase Management API & Auth Admin from your IDE — with built-in safety controls.
Query local DuckDB files, in-memory DBs, S3, or MotherDuck cloud with read/write SQL.
Official Chroma server: create collections and run vector, full-text, and metadata search.
Official Pinecone server: manage indexes, upsert/search records, rerank, and search Pinecone docs.
Read and write access to Airtable bases — inspect schemas, query, and modify records, tables, fields, and comments.
Connect Claude directly to PostgreSQL, MySQL, SQLite, Oracle, MS SQL and other SQLAlchemy databases.
Give AI assistants structured access to MySQL, PostgreSQL, SQLite, Oracle, and TimescaleDB simultaneously.
Chat with your robotics, drone, and IoT data — deterministic SQL over ROS, PX4, ArduPilot & Betaflight logs.
Ingest, search, and RAG over data from Slack, Discord, Google Drive, GitHub, Jira, Linear and more via Graphlit.
Query, explore, and govern Apache Doris databases via MCP — NL2SQL, metadata, and analytics tools.
Let AI assistants work directly with Firebase Firestore, Storage, and Authentication.
Connect LLMs to the Milvus vector database for vector, text, and hybrid search plus collection management.
Full-featured MCP server for querying, aggregating, and managing MongoDB databases via natural language.
Query Snowflake databases over MCP — read/write SQL, schema discovery, and data-insight memos.
MCP server for MySQL database operations: query, execute, list and describe tables via prepared statements.
Manage Confluent Cloud, Confluent Platform & Apache Kafka via natural language — 50+ tools across Kafka, Flink, Schema Registry & more.
Inspect BigQuery schemas and run SQL queries from your LLM client.
Comprehensive SQLite database interaction over MCP: CRUD, introspection, and custom SQL queries.
High-performance Go MCP server that lets AI assistants run SQL queries and explore data across a Trino cluster.
Safe, read-only SQLite database exploration and querying for LLMs, built on FastMCP.
Prisma's official MCP: run migrations, provision Prisma Postgres, execute SQL and manage backups from your agent.
Universal interface between AI agents and Alibaba Cloud Hologres — query metadata, run SQL, diagnose performance.
Official MCP server for InfluxDB 3 (Core/Enterprise/Cloud) — query, write, and manage databases and tokens.
Let LLMs query Couchbase clusters, run SQL++, manage documents, and analyze query performance.
Manage Kafka Schema Registry from Claude — register, evolve, compare, migrate, and export Avro schemas in plain language.
Query and analyze GreptimeDB observability data (metrics, logs, traces) via SQL, TQL, and RANGE queries.
Query and explore YDB databases from any MCP-compatible LLM using natural language.
Manage Turso databases and run SQL from an agent, with separate read-only and destructive query tools.
Use these in a stack
FAQ
Why does schema inspection matter for AI agents?
LLMs hallucinate table and column names. Giving the agent a tool to list tables and describe schema first dramatically cuts wrong-query errors.
Do these work with NoSQL too?
Some do — document stores expose collection/index listing tools that play the same role as table introspection in SQL databases.