MCP Servers

Official MCP server for Qdrant vector search engine. Acts as a semantic memory layer enabling AI agents to store and retrieve information using vector similarity search. Supports storing text with metadata, semantic querying, configurable embedding models via FastEmbed, and both cloud-hosted and local Qdrant instances. Useful for building RAG pipelines, code search, knowledge bases, and long-term agent memory.

Provides AI agents with access to PostHog product analytics through the Model Context Protocol. Enables querying events, analyzing funnels, inspecting feature flags, and reviewing session recordings metadata. Supports HogQL queries for advanced analytics and cohort analysis for user segmentation.

MCP server for MySQL and MariaDB that lets AI agents inspect schemas, list tables, and run parameterized SQL queries. Supports read-only or read-write modes so agents can explore data, debug, and prototype against a MySQL database with controlled access.

Official Snowflake MCP server enabling AI agents to query and analyze data in the Snowflake AI Data Cloud. Supports running SQL against warehouses, exploring databases and schemas, describing tables, and invoking Cortex AI services for search and analytics, with role-based access control honored end to end.

MCP server for Sentry error tracking integration. Enables AI agents to retrieve and analyze issues, view error stack traces, search events by query, and access project performance data. Helps developers debug production errors by providing contextual error information directly in AI-powered development workflows.

MCP server for Salesforce that lets AI agents query and modify CRM data using SOQL, manage standard and custom objects (Accounts, Contacts, Opportunities, Cases), describe object metadata, and execute Apex anonymous blocks. Supports both production and sandbox orgs via OAuth or username-password flows.

MCP server for the Weaviate open-source vector database. Enables AI agents to store objects, run semantic and hybrid searches, and manage collections, making it a memory and retrieval backend for RAG applications directly from AI-powered tools.

Official MCP server for the Milvus vector database. Lets AI agents create collections, insert vectors, and run similarity and scalar-filtered searches over large-scale embedding data, enabling retrieval and long-term memory for AI applications.

Official Linear MCP server for project management integration. Enables AI agents to find, create, and update issues, projects, and comments in Linear. Supports searching issues by status, assignee, or label, creating new issues with full metadata, and managing project workflows directly from AI-powered development environments.

Provides read-only access to PostgreSQL databases through the Model Context Protocol. Enables AI agents to inspect database schemas, run SELECT queries, and explore table structures. Designed for safe database exploration with read-only transaction isolation to prevent accidental data modification. Originally part of the reference servers, now archived and available in servers-archived.

E2B's MCP server gives AI agents the ability to run arbitrary code in secure, isolated cloud sandboxes. Each sandbox is a fast-booting micro-VM where models can execute Python and shell commands, install packages, read and write files, and capture stdout/stderr — ideal for code interpretation, data analysis, and agentic workflows that need real execution.

A Model Context Protocol server for Google Drive that lets AI assistants list, search, and read files stored in Drive, with automatic export of Google Docs, Sheets, Slides, and Drawings to readable formats. Authenticates via OAuth 2.0 and exposes Drive files as MCP resources so agents can ground their answers in your documents without copying data into chat first.

Pinecone's official MCP server connects AI assistants to Pinecone vector databases for retrieval-augmented generation (RAG) workflows. Lets agents create and configure indexes, upsert and embed documents, and run semantic searches over vector data — all from natural language, without leaving the editor or chat.