"Multi-agent AI systems for collaborative code development" matching MCP servers:

Exposes a single HTTP endpoint that aggregates tool definitions from GitHub, Kubernetes, and database namespaces, letting clients list available tools and invoke them by name. It provides health-check, tool-discovery, and tool-call routes for local, read-only experimentation without calling hosted models or applying production changes.

Read-only MCP server for querying PostgreSQL, MySQL, and SQLite from AI agents — multi-database, safe by default.

A knowledge graph memory server using SQLite to provide persistent, isolated contexts for organizing information into searchable categories like work and personal projects. It features unique ID-based operations and a token-efficient serialization format designed to optimize interactions with LLMs.

MCP server that allows Claude AI to interact directly with MySQL databases, enabling query execution and table information retrieval through natural language.

Enables read-only SQL queries across several named MySQL/MariaDB/Aurora and Postgres databases from one place, with tools to list databases, tables, and describe schemas. It enforces safety by requiring non-local hosts to be read replicas and by running every statement in a rolled-back read-only transaction.

Lets AI clients ask natural-language questions about a SQL database with production-safe guardrails, schema grounding, and read-only enforcement.

Enables querying multiple SQL Server, Azure SQL, or Synapse databases through a single MCP interface, with support for read-only targets and various authentication methods.

A multi-purpose MCP server for AI-powered healthcare assistance that processes clinical data through configurable LLM providers. Maintains webhook endpoints for patient data processing with PostgreSQL logging and OpenAPI documentation.

Enables LLM clients to inspect and query your own GCP and AWS infrastructure, including BigQuery/Athena, CI build systems, container/serverless runtimes, and their logs through configurable environments.

An MCP server for managing multiple MySQL and MariaDB database connections simultaneously, allowing users to run SQL queries and manage schemas through AI-powered tools. It features dynamic connection management, persistent configuration, and granular tools for database, table, and index operations.

Enables governed access to corporate Postgres databases via MCP, supporting read-only queries, confirmed data and schema changes, query explanation, audit trail retrieval, and role-based policies with optional Vault secret integration.

A version-agnostic MCP server for Odoo that enables AI agents to interact with any Odoo app's data, schema, and source code, supporting tasks like data CRUD, schema mapping, code analysis, and feature implementation.

An oil & gas data-analytics MCP server that enables guarded SQL queries, well valuation, and map rendering within chat apps.

A ready-to-run MCP gateway and multi-agent scheduling system with 14 built-in tools and 3-layer performance optimization, reducing latency by 65%.

Enables AI coding assistants to query and manage multiple MySQL and MariaDB databases through a single MCP server, with SQL injection protection and read-only mode by default.

A Model Context Protocol server that provides read-only access to PostgreSQL databases with enhanced multi-schema support, allowing LLMs to inspect database schemas across multiple namespaces and execute read-only queries while maintaining schema isolation.

Enables AI agents to query and explore multiple MonetDB column-store databases from one server, using named config labels or runtime credentials via dynamic connect. Provides SQL execution, schema/table inspection, health checks and EXPLAIN plans, with read-only defaults and per-project restriction flags like --label and --no-dynamic.

Enables LLMs to orchestrate AI agents and tasks, inspect DAG workflows, monitor cluster metrics, and perform safe database queries and statements through standardized MCP tools.

Enables AI applications to discover MySQL and PostgreSQL database schemas and run validated read-only SELECT queries against a configured database, with result limits and SQL safety controls.

A simple program that helps you connect to many PostgreSQL databases at once, providing read-only access and hot-reload configuration.