Data & contentPublic source

Database MCP Server

Database operations for AI agents — query, schema inspection, migrations, explain plans, performance analysis, and data exploration. 22 tools with read-only defaults and governed writes.

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Provides database capabilities through a typed MCP contract.

Architecture

How Database MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

Database MCP Server

Validates the request and owns 22 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

Database MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Database MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

22 named tools

list_tables

All tables/collections in the database

see documentation

describe_table

Columns, types, constraints, indexes

see documentation

get_relationships

Foreign keys and references

see documentation

list_indexes

All indexes on a table

see documentation

get_database_stats

DB size, table sizes, row counts

see documentation

search_schema

Find tables/columns by name

see documentation

query

Execute read-only SQL (SELECT only)

see documentation

sample_data

Get sample rows from a table

see documentation

filter_table

Query with filters, ordering, pagination

see documentation

explain_query

Get EXPLAIN/query plan

see documentation

get_column_stats

Distinct values and distributions

see documentation

execute

Run INSERT/UPDATE/DELETE

see documentation

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

22 see documentation

Read-only by default — query tool only allows SELECT statements
Writes are gated — execute and run_migration are classified as gated writes
No data stored — MCP is a pure API passthrough
Parameterized queries — prevents SQL injection via params array

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

ADK MCP SDKrmcp

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-database

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-database",
    ["mcp-database"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md Overview ↗test/README.md Architecture ↗docs/assets/architecture.svg Issues and support ↗github.com issues

Keep exploring