"Querying Elasticsearch (ES)" matching MCP servers:

Enables localized file system operations such as listing, reading, editing, creating, deleting, and searching files, scoped to the directory where the server is invoked.

A comprehensive Model Context Protocol server that integrates Elasticsearch search with file operations, document validation, and version control to transform AI assistants into powerful knowledge management systems.

Standalone TypeScript MCP server for filesystem operations with robust security, encoding support, and cross-platform path handling.

Enables AI assistants to create and manage GameMaker Studio 2 project resources — scripts, objects, events, rooms, PNG sprites, PCM WAV sounds, GLSL ES shaders and virtual groups — through local stdio tools. Every change can be previewed with dry runs, checked for conflicts, and undone via transaction backups.

Provides Claude with safe read/write access to Obsidian vaults, with YAML frontmatter protection and path filtering to prevent corruption.

A small filesystem MCP server that reads and writes files under one confined root over stdio, with paginated tools and strict change-detection. It enables safe, deterministic file access for agentic runtimes and MCP clients.

Provides batch file operations, search, and essential git workflows via stdio MCP.

A Model Context Protocol server that provides intelligent file reading and semantic search capabilities across multiple document formats with security-first access controls.

Hosted filesystem MCP server over HTTP with auth. Enables reading, writing, editing, searching, and listing files via MCP tools like grep, glob, and tree.

Ultra-fast, memory-efficient Rust implementation of the Filesystem MCP server with bounded IO, regex search, and optional terminal execution.

Enables read-only SQL querying and exploration of data files (CSV, Parquet, JSON, Excel, etc.) via DuckDB, supporting local paths, globs, URLs, and S3 buckets.

Enables querying and updating Markdown frontmatter metadata using DuckDB SQL, with optional semantic search capabilities for finding similar documents based on content.

Enables secure filesystem operations with directory sandboxing and optional read-only mode. Supports file reading/writing, directory management, file searching, and text operations while restricting access to specified directories.

An MCP server that provides AI agents with a persistent, PostgreSQL-backed virtual filesystem, supporting session-isolated file operations, cross-session shared stores, and glob/grep search.

Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of silently overwriting, then reacquires and retries. Single-host, TLA+-verified.

A collection of Model Context Protocol servers that enable Claude Desktop to provide development assistance capabilities with filesystem, Git, shell command, and web search functionality without incurring API usage costs.

Enables AI agents to efficiently process large local and online PDFs through selective extraction of text, images, and metadata. It provides tools for content search and document outline navigation to optimize context window usage.

Enables Claude Code and Claude Desktop to access Hansung University’s LMS (Cosmos) for assignment, quiz, VOD, and course-material workflows, including deadline lists, downloading assignments and materials, weekly summaries, and local lecture transcription, without submitting work.

Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.

MCP server for advanced Arabic Microsoft Word document creation, formatting, XML manipulation, and text repair with full RTL support. It enables users to generate, inspect, and modify .docx files through natural language and 13 specialized tools.