MindsDB Supercharges Google's MCP Toolbox with Unstructured Data Support

Source: Dev.to

The MindsDB integration at a glance

MindsDB is a federated query engine designed specifically for AI applications. It acts as a universal translator, enabling you to query hundreds of data sources (structured, semi‑structured, unstructured) using familiar SQL. We’ve contributed this capability as a new connector into MCP Toolbox, allowing developers and AI agents to seamlessly interact with a broader spectrum of enterprise data through MindsDB.

Now, with MindsDB, MCP Toolbox can connect to hundreds of data sources, including popular business applications like Salesforce, Jira, and GitHub, as well as unstructured data sources such as Gmail and Slack. This means you can break down data silos and connect all your data from a single API to your AI applications. Typical use cases include AI‑powered search, analytics, and real‑time data for agentic applications.

Key features: Bridging structured and unstructured worlds

• Datasource expansion – Instantly gain access to a massive catalog of new data sources. Query Salesforce opportunities alongside GitHub activity, or analyze email patterns with Slack conversations—all through a unified interface.
• SQL interface for any data – Write standard SQL queries that automatically translate to various API protocols (REST, GraphQL, native protocols). This reduces the complexity and learning curve associated with accessing diverse data.
• Cross‑datasource AI analytics – Perform joins and analytics across different sources. For example, correlate sales data from Salesforce with development activity from GitHub to obtain a holistic view of business operations. MindsDB treats each source—structured or unstructured—as a virtual table, enabling sophisticated SQL operations across all sources.
• Access to unstructured data – Over 200 connectors let you index text data and query it with SQL.
• Knowledge Bases for unstructured data – Create autonomous Retrieval‑Augmented Generation (RAG) systems. Ingest emails (Gmail/Outlook), messages (Slack, Microsoft Teams, Discord), and files (S3, local files) into Knowledge Bases. Once ingested, the data becomes queryable by AI applications or models. An auto‑generated data catalog provides metadata and a relational model across all sources, while hybrid search (vector similarity + keyword) surfaces the most relevant results for AI search and analytics use cases.

Technical implementation updates

• New MindsDB source implementation – The Toolbox now includes a MindsDB source that leverages the MySQL wire protocol for robust connectivity.
• Comprehensive test coverage – Extensive unit and integration tests ensure reliability and backward compatibility with existing SQL features.
• Dedicated MindsDB tools – mindsdb-execute-sql for direct SQL execution and mindsdb-sql for parameterized queries provide enhanced flexibility.

Quickstart Guide

1. Set up the MCP Toolbox
   Ensure the MCP Toolbox service is running. Detailed instructions are available in the official documentation.

2. Install MindsDB
   The fastest way to get MindsDB up and running is via Docker:

   docker run --name mindsdb_container \
     -e MINDSDB_APIS=http,mysql \
     -p 47334:47334 -p 47335:47335 \
     mindsdb/mindsdb

   For other installation options (e.g., PyPI), refer to the MindsDB documentation.

3. Connect your data sources in MindsDB
   Within MindsDB, create “databases” that connect to your external sources, such as:

   • Salesforce
   • GitHub
   • Gmail

   Follow the respective integration guides to configure each connector.

Connecting Data Sources in MindsDB

Typical usage involves CREATE DATABASE statements. Example:

-- connect to Salesforce
CREATE DATABASE salesforce_datasource
WITH
    ENGINE = 'salesforce',
    PARAMETERS = {
        "username": "your-username@email.com",
        "password": "your-password",
        "client_id": "your-client-id",
        "client_secret": "your-client-secret"
    };

-- connect to PostgreSQL
CREATE DATABASE postgresql_datasource 
WITH
    ENGINE = 'postgres',
    PARAMETERS = {
        "host": "postgres.sample.com",
        "port": 5432,
        "database": "postgres",
        "user": "postgres",
        "schema": "data",
        "password": "password"
    };

Refer to the MindsDB documentation for specific connector details.

4. Use MindsDB Tools in MCP Toolbox

The MindsDB integration within MCP Toolbox allows you to execute SQL queries across your connected MindsDB data sources. You can use tools like mindsdb-execute-sql for direct querying.

-- run federated queries
SELECT *
FROM salesforce_datasource.account a
JOIN postgresql_datasource.customer_int c
  ON a.`Id` = c.`AccountId`;

5. Unify Data into the Knowledge Base

Load data into a MindsDB Knowledge Base, which is useful for semantic search over large, unstructured data sets.

CREATE KNOWLEDGE_BASE my_kb
USING
    embedding_model = {
        "provider": "openai",
        "model_name": "text-embedding-3-large",
        "api_key": "sk-..."
    },
    reranking_model = {
        "provider": "openai",
        "model_name": "gpt-4o",
        "api_key": "sk-..."
    },
    storage = my_vector_store.storage_table,
    metadata_columns = ['AccountId', 'Created_At', ...],
    content_columns = ['Description', 'Notes', ...],
    id_column = 'Id';

INSERT INTO my_kb
SELECT *
FROM salesforce_datasource.account a
JOIN postgresql_datasource.customer_int c
  ON a.`Id` = c.`AccountId`;

Learn more about knowledge bases here.

Resources

• MCP Toolbox GitHub repo:
• MindsDB in MCP Toolbox:
• MindsDB Documentation:
• MindsDB GitHub: