"A search about the concept and practice of magic" matching MCP servers:

Enables read-only FHIR access to Practice Fusion EHR to search patients, appointments, conditions, medications, and lab results.

MCP server that exposes read-only tools to query a passport applications database, enabling an AI assistant to check application status without exposing personal applicant details.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

Search the fastest-growing US horse boarding directory: 6,000 facilities and 3,800 trainers across 48 states, plus boarding price data by state.

Enables AI assistants to interact with Databricks workspaces, running SQL queries, managing jobs, and exploring schemas via the Model Context Protocol.

Exposes a governed dbt MetricFlow semantic layer to AI agents through three tools — list metrics, list dimensions and query metrics — so questions about federal contract spend are answered from defined metrics rather than raw tables. Guardrails reject undefined metrics, raw columns, SQL in filters and bulk exports, and no tool can execute SQL.

Read-only MCP server that proxies The Game Pensieve API over Streamable HTTP, letting AI assistants query a personal game collection via tools like search, filters, and summaries. Supports OAuth 2.1 enforcement and owner-scoped access.

Enables full-text search of macOS iMessages including link preview metadata. Works as an MCP server for Claude Desktop to search your messages locally.

Downloads your entire Search Console dataset into a local SQLite database, then gives your LLM a pre-built SQL query library for every standard SEO analysis type, with context available for your LLM to perform any SQL query to answer your questions and analyse for you.

Enables AI systems to perform full-text and semantic search operations over structured/unstructured data in Azure Cognitive Search, with capabilities for document indexing and management through natural language.

MCP server that aggregates job listings from Remotive and Arbeitnow, with local SQLite caching, application tracking, and saved searches.

Enables AI assistants to discover and invoke CRUD tools and read-only resources over the Model Context Protocol for generated API services.

Exposes generated CRUD services to LLM clients over the Model Context Protocol, providing tools for create, update, and delete actions plus read-only resources for listing and fetching records by id. It lets assistants like Claude, ChatGPT, and Cursor discover and manipulate the same data served by the project's REST endpoints without any extra glue code.

Exposes every generated CRUD service to LLM clients such as Claude, ChatGPT, or Cursor through discoverable MCP tools for create, update, and list actions plus read-only resources, so models can query and manipulate data without raw HTTP calls. It runs alongside the same codebase's REST endpoints, letting clients and AI share one data layer.

Enables LLMs to discover and invoke generated CRUD tools and resources, allowing AI assistants to interact with the same data exposed by the REST API. Supports MCP clients such as Cursor and Claude over HTTP.

Enables LLMs and AI assistants to discover and use tools and resources for CRUD operations on generated services, providing direct interaction with the same data exposed by REST endpoints.

Enables AI agents to search and retrieve UK company data, including company details by Companies House number, group ownership structures, website associations, and Real-Time Industrial Classification definitions.

Enables LLMs to discover and invoke CRUD tools and read-only resources for generated services, allowing direct interaction with the same data exposed by the REST API.

Enables LLMs to interact with generated REST API services by exposing MCP tools and resources for CRUD operations, listing, and retrieval. It lets AI clients discover and call create, update, delete, list, and get-by-id actions against the same data available over REST.

Enables LLMs to interact with generated CRUD services through MCP tools and resources, so they can create, update, list, and fetch records via a standard protocol. It also provides REST API access from the same codebase for traditional clients.

A Model Context Protocol server that searches transcript segments in a Turso database using vector similarity, allowing users to find relevant content by asking questions without generating new embeddings.

Enables LLMs to discover and invoke generated API operations as MCP tools and resources, supporting create, update, list, and get-by-id actions over the same data exposed by the REST API.

Enterprise MCP server providing a suite of tools including file, database, GitHub, Slack, calendar, email, vector search, and Python execution, with safe defaults and OpenAI integration for automatic tool selection.

It enables AI assistants to discover and invoke CRUD operations as MCP tools and read application data through MCP resources, allowing natural-language interaction with the generated backend.

It enables LLMs to interact with generated REST APIs by exposing CRUD operations as MCP tools and readable records as MCP resources. This lets AI clients discover and manage API data through the Model Context Protocol.

Enables LLMs to discover and invoke CRUD operations and read-only data resources for generated services through the Model Context Protocol, alongside traditional REST endpoints.

Enables AI agents to discover and query data federated across MySQL/MariaDB, PostgreSQL, ClickHouse, S3 and Kafka with SQL, exposing tools to list databases, schemas, tables and connections, describe columns, search objects, inspect table statistics, run EXPLAIN, and execute arbitrary statements. It runs locally over stdio against a PostgreSQL-wire endpoint and returns structured results or SQLSTATE-coded errors.

Provides access to Naver Search APIs, allowing AI agents to search across multiple categories (blogs, news, books, images, shopping items, etc.) with structured responses optimized for LLM consumption.

Enables searching for any text within a specified Algolia index through an MCP-compatible interface. It allows users to integrate Algolia search capabilities into their environment using an application ID and API key.