"Calibre-Web" matching MCP servers:

Surfaces your Calibre e-book catalog to Claude via the Model Context Protocol, enabling search, metadata management, and library maintenance through natural language.

Read-only MCP server that runs inside Calibre as a plugin, exposing the live Calibre library for inspection, search, metadata, and duplicate detection via Streamable HTTP.

A read-only MCP server for an existing Calibre ebook library, enabling metadata search, full-text search, and category browsing via the Model Context Protocol.

Lets AI agents read and write the Calibre Ebook Translator plugin's translation cache chunk by chunk, enabling direct book translation workflows without manual copy-paste.

A local stdio MCP server that enables AI tools to search a self-hosted Calibre library over SSH, supporting metadata queries, full-text search, and book details.

Enables read-only access to local Calibre libraries for searching metadata, inspecting book formats, and extracting content samples. Supports full-text search, batch operations, and detailed book analysis through natural language queries.

Enables LLMs to extract content from websites using automated static and dynamic scraping engines with built-in anti-bot protections. It provides tools for web data retrieval and stores results in MongoDB with support for JSON and CSV exports.

Enables read-only querying of Moodle as a student, including courses, assignments, grades, forums, and files, using a personal web services token.

Enables natural-language (Chinese or English) querying of a socioeconomic survey microdata warehouse covering five survey programs and over a thousand tables, by exposing standard tools for exploring surveys and sections, semantically searching variable metadata, generating read-only SQL, computing weighted statistics, and rendering charts. Results, SQL, and tool calls are returned in-chat, and it can be attached to Claude Desktop or Claude Code as well as its bundled web interface.

Enables MCP-compatible agents to interact with multiple Dataverse environments via the Dataverse Web API, supporting data operations, metadata inspection, solution management, and other Power Platform development tasks using Azure CLI authentication.

Provides filesystem, web search, SQLite, and system tools for AI assistants like Claude, enabling secure access to local resources and the web.

A universal resource server that enables AI models to mount local folders, scrape web pages into Markdown, and query SQLite databases without writing code. It features a real-time TUI dashboard and persistent configuration for managing diverse knowledge sources.

A Python web-scraping toolkit that exposes 22 tools for fetching structured web data (from any URL to search, finance, e-commerce, and reference sources) as validated JSON for AI agents.

Read-only MCP server for Odoo.sh exposing builds, environments, logs, and system status via Web API and SSH without any write capabilities.

A secure MCP server that lets AI assistants directly interact with PostgreSQL databases via tools like create_table, list_tables, and execute_sql, plus a web configurator for managing connections.

A minimal MCP server that gives AI coding agents clean read and write access to Microsoft Dataverse environments via the Dataverse Web API v9.2. It works as a drop-in alternative to Microsoft's own MCP server, without requiring Copilot Credits or managed environments.

QuestDB MCP server connects coding agents to a running QuestDB Web Console. The agent gets tools to create notebook cells, run queries, and build charts.

Enables AI agents to query, inspect, and manage Microsoft Dataverse records, metadata, schema, forms, views, and Power Platform environments via the Dataverse OData Web API.

Enables schema operations in Microsoft Dataverse using the Model Context Protocol, allowing users to create and manage tables, columns, relationships, and option sets through the Dataverse Web API.

Enables AI assistants to read and write a self-hosted Gramps Web family tree through the REST API, creating facts with citations attached and auditing unsourced or duplicate data with 83 evidence-disciplined tools. It also exposes legacy GEDCOM exports as a read-only reference layer of untrusted hints, with living-person privacy filtering on by default.