Overview
TiDB Cloud MCP Server brings live TiDB Cloud access into MCP-compatible agents and developer tools. It gives those clients a direct path to real schema and data, which is far more useful than asking an agent to reason from screenshots, copied DDL, or stale sample rows.
Delivered as a container image for Amazon Bedrock AgentCore Runtime, the server runs in your AWS environment and connects to the TiDB Cloud deployment you specify. You control the target cluster, the credentials, and the database privileges exposed to agents. That makes it possible to keep one deployment read-only for inspection workloads while reserving broader access for tightly controlled operational flows.
The current toolset includes show_databases, switch_database, show_tables, db_query, db_execute, db_create_user, and db_remove_user. Together, these tools support common workflows such as schema discovery, SQL-assisted debugging, application development against live TiDB Cloud data, and selected database administration tasks carried out through the MCP interface.
This product is intended for teams that already use TiDB Cloud and want to make that database context available to AI systems without building a custom MCP layer from scratch. Buyers must provide an existing TiDB Cloud deployment, valid database credentials, and network connectivity from the runtime environment to the target endpoint. If your TiDB Cloud environment uses IP allowlists, add the required addresses before testing.
Highlights
- Give AI agents live TiDB Cloud context instead of static schema notes, exported data, or manually prepared samples.
- Control which cluster, credentials, and database privileges are exposed to agents by running the MCP server in your own AWS environment.
- Support schema discovery, SQL-assisted investigation, application development, and selected database operations through a single MCP server deployment.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
This is a free offering.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
AgentCore Runtime deployment
- Amazon Bedrock AgentCore
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Version 1 of TiDB MCP Server
Additional details
Usage instructions
Subscribe to the product and deploy the container on Amazon Bedrock AgentCore Runtime.
Provide the required environment variables:
TIDB_HOST TIDB_PORT TIDB_USERNAME TIDB_PASSWORD TIDB_DATABASE
The runtime environment must be able to reach your TiDB endpoint. If your TiDB Cloud deployment uses IP allowlists, add the required outbound addresses before testing.
After deployment, the server listens on port 8000 and exposes the MCP endpoint at POST /mcp.
Validate the deployment with MCP initialization and tools/list, then test one or more supported tools such as show_databases, show_tables, or db_query.
Use a database account with privileges appropriate for your use case. This server can expose write and administrative operations such as db_execute, db_create_user, and db_remove_user.
For deployment and configuration details, see https://docs.pingcap.com/ai/tidb-mcp-server/ . For more information about TiDB Cloud, see https://docs.pingcap.com/tidbcloud/ .
Resources
Vendor resources
Support
Vendor support
Please contact us at aws-marketplace@pingcap.com for more information.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.