数据库 连接器
18 个预置 数据库 连接器 — 共 211 个 MCP 工具：Databricks, Supabase, Firebase。粘贴凭据，智能体即可调用。无需编写 MCP 服务器。
Query a Microsoft SQL Server database directly: list tables, describe columns and run read-only T-SQL. Supports SQL Server and Windows (NTLM) authentication. Installs read-only.
Query a PostgreSQL database directly: list tables, describe columns and run read-only SQL. Installs read-only; credentials are held encrypted rather than in the connection string.
Let your AI search and inspect your Algolia indices: list indices, search and browse records, read settings, synonyms and Rules, see top searches and searches without results and, with your confirmation, add or update records.
Let your AI explore and query Google BigQuery: list projects, datasets and tables, read schemas, preview rows for free, estimate a query's cost with a dry run before running it, page through results and check the job history. Signs in with your Google account.
Let your AI work with your Bubble app's data: see which data types and backend workflows it exposes, search and read things; with your confirmation create or change things and run backend workflows.
Read-only SQL on a ClickHouse server or ClickHouse Cloud service over the HTTP interface: databases, tables, columns, CREATE statements, table sizes, running and recent queries, and any SELECT with readonly=1.
Let your AI work with your Databricks workspace: run SQL on a warehouse, explore Unity Catalog catalogs, schemas and tables, check clusters, warehouses, jobs and runs, read notebooks, and start or stop compute or trigger jobs after your confirmation. With a personal access token.
Let your AI explore and query your Elasticsearch cluster on Elastic Cloud, Serverless or your own servers: list indices and data streams, read mappings, search, aggregate, count, run ES|QL and, with your confirmation, write documents.
Let your AI work with Firebase: list projects and apps, browse and query Cloud Firestore, create and update documents, look up and disable Authentication users, read Remote Config, and (switched off by default) publish Remote Config or send push notifications. Signs in with your Google account.
Let your AI work with Glide Big Tables: list the tables of your Glide team and read their rows; with your confirmation add rows and update a row.
Query a MongoDB database directly: introspect collections and their field shapes, and run read-only find queries with filter, projection, sort and limit. Installs read-only; credentials are held encrypted rather than in the connection string.
Query a MySQL or MariaDB database directly: list tables, describe columns and run read-only SQL. Installs read-only; credentials are held encrypted rather than in the connection string.
Let your AI manage Neon serverless Postgres: projects, branches, compute endpoints, databases, roles, schemas, operations and consumption. It can create branches and start or suspend computes after your confirmation. Never returns passwords. With a Neon API key.
Query an Oracle database directly: list tables, describe columns and run read-only SQL. Installs read-only; credentials are held encrypted rather than in the connection string.
Let your AI search your Pinecone vector database: list indexes, run semantic and keyword search, query and fetch records, check namespaces and stats, embed and rerank with Pinecone Inference, chat with your Pinecone Assistants and, with your confirmation, add records.
Ask your Snowflake data questions from Claude, ChatGPT or Copilot through Snowflake's official managed MCP server: Cortex Agents, Cortex Analyst semantic views, Cortex Search and your own functions, governed by your Snowflake roles.
Let your AI work with Softr: browse Softr Databases, tables and fields, list, search and read records; with your confirmation create and update records, add users to a Softr app and create magic sign-in links.
Let your AI look after your Supabase projects: list projects and check their health, explore schemas and tables, run read-only SQL, read logs, security and performance advisors, Edge Functions, migrations, branches and storage buckets. Through the Management API with a personal access token.
按分类浏览
全部 18 个连接器（A–Z）
缺少连接器?用一份 JSON 添加它。
每个适配器都是 packages/backend/src/adapters/ 下的单个 JSON 文件。复制一份现有的、替换端点和认证、提交 PR — 构建时由参数化测试验证。
// adapters/de/my-adapter.json
{
"slug": "my-erp",
"name": "My ERP",
"category": "erp",
"authType": "BEARER_TOKEN",
"tools": [/* ... */]
}