Happy slice of mcp pizzaMCP.pizza

anyquery

MCP.Pizza Chef: julien040

Anyquery is an MCP server that allows users to query over 40 different data sources, including GitHub and Notion, using SQL. It acts as a powerful bridge enabling large language models such as ChatGPT and Claude to access and retrieve structured data from diverse platforms through the Model Context Protocol. This server simplifies data integration and querying by providing a unified SQL interface, making it ideal for developers and AI workflows that require real-time, structured data access from multiple APIs and services. Anyquery enhances AI capabilities by enabling dynamic, multi-source data retrieval within conversational or automated environments.

Use This MCP server To

Query GitHub repositories with SQL Access Notion databases via SQL queries Integrate 40+ data sources into AI workflows Enable LLMs to fetch structured data dynamically Unify API data access under SQL interface Automate data retrieval for AI agents Support multi-source data querying in real-time

README

Anyquery

Anyquery logo

GitHub Downloads (all assets, all releases) GitHub commit activity Documentation GitHub issues Dynamic JSON Badge Dynamic JSON Badge Go Reference

Anyquery is a SQL query engine that allows you to run SQL queries on pretty much anything. It supports querying files, databases, and apps (e.g. Apple Notes, Notion, Chrome, Todoist, etc.). It's built on top of SQLite and uses plugins to extend its functionality.

It can also connect to LLMs (e.g. ChatGPT, Claude, Cursor, TypingMind, etc.) to allow them to access your data.

Finally, it can act as a MySQL server, allowing you to run SQL queries from your favorite MySQL-compatible client (e.g. TablePlus, Metabase, etc.).

Anyquery header

Usage

Connecting LLM

LLMs can connect to Anyquery using the Model Context Protocol (MCP). This protocol provides context for LLMs that support it. You can start the MCP server with the following command:

# To be started by the LLM client
anyquery mcp --stdio
# To connect using an HTTP and SSE tunnel
anyquery mcp --host 127.0.0.1 --port 8070

You can also connect to clients that supports function calling (e.g. ChatGPT, TypingMind). Refer to each connection guide in the documentation for more information.

# Copy the ID returned by the command, and paste it in the LLM client (e.g. ChatGPT, TypingMind)
anyquery gpt

5ire example

Running SQL queries

The documentation provides detailed instructions on how to run queries with Anyquery. But let's see a quick example. Type anyquery in your terminal to open the shell mode. Then, run the following query:

Anyquery SQL examples

You can also launch the MySQL server with anyquery server and connect to it with your favorite MySQL-compatible client.

anyquery server &
mysql -u root -h 127.0.0.1 -P 8070

Installation

The documentation provides detailed instructions on how to install Anyquery on your system. You can install anyquery from Homebrew, APT, YUM/DNF, Scoop, Winget and Chocolatey. You can also download the binary from the releases page.

Homebrew

brew install anyquery

APT

echo "deb [trusted=yes] https://apt.julienc.me/ /" | sudo tee /etc/apt/sources.list.d/anyquery.list
sudo apt update
sudo apt install anyquery

YUM/DNF

echo "[anyquery]
name=Anyquery
baseurl=https://yum.julienc.me/
enabled=1
gpgcheck=0" | sudo tee /etc/yum.repos.d/anyquery.repo
sudo dnf install anyquery

Scoop

scoop bucket add anyquery https://github.com/julien040/anyquery-scoop
scoop install anyquery

Winget

winget install JulienCagniart.anyquery

Chocolatey

choco install anyquery

Plugins

Anyquery is plugin-based, and you can install plugins to extend its functionality. You can install plugins from the official registry or create your own. Anyquery can also load any SQLite extension.

Integrations

License

Anyquery is licensed under the AGPLv3 license for the core engine. The RPC library is licensed under the MIT license so that anyone can reuse plugins in different projects.

The plugins are not subject to the AGPL license. Each plugins has its own license and the copyright is owned by the plugin author. See the LICENSE file for more information.

Contributing

If you want to contribute to Anyquery, please read the contributing guidelines. I currently only accept minor contributions, but I'm open to any suggestions or feedback.

You can have a brief overview of the project in the architecture documentation.

anyquery FAQ

How do I connect Anyquery to my data sources?
You configure Anyquery by adding your data source credentials and endpoints through its integration registry, enabling SQL queries across supported platforms.
Can Anyquery handle authentication for services like GitHub and Notion?
Yes, Anyquery supports authentication mechanisms required by each data source, allowing secure access to private data.
How does Anyquery integrate with LLMs like ChatGPT or Claude?
Anyquery exposes a standardized SQL querying interface via MCP, letting LLM clients send queries and receive structured responses seamlessly.
Is it possible to add custom data sources to Anyquery?
Yes, Anyquery's plugin system allows developers to add new integrations beyond the default 40+ supported sources.
What kind of SQL syntax does Anyquery support?
Anyquery supports standard SQL queries tailored to the schema of each connected data source, enabling familiar query patterns.
How do I monitor query usage and performance in Anyquery?
Anyquery provides logging and metrics to track query counts, response times, and integration health via its dashboard and API.
Does Anyquery support real-time data updates?
While Anyquery queries live data sources, real-time update support depends on the underlying API capabilities of each integration.
What are the security considerations when using Anyquery?
Anyquery enforces secure authentication, scoped access tokens, and encrypted communication to protect data privacy and integrity.