"Running queries in Apache Superset" matching MCP servers:

A Model Context Protocol server that provides seamless access to multiple storage services including S3, Azure Blob Storage, and Google Cloud Storage through Apache OpenDAL™.

MCP server for lossless YAML 1.2 editing by AI agents. Two tools — noyalib_get (read a value at a dotted/indexed path) and noyalib_set (write a value, preserving comments/formatting byte-for-byte). Pure Rust, streaming-first serde, JSON Schema validation. MIT OR Apache-2.0.

Enables any MCP-compatible AI, whether in the browser or running locally, to create and edit projects, run terminal commands and long-running jobs, and optionally use Docker, all guarded by a policy engine, workspace jail, authentication, and audit logging.

A unified set of developer tools including file search/replace, SQLite queries, HTTP requests, port inspection, system monitoring, and Git status, accessible via natural language in MCP-compatible clients.

An MCP server built with FastMCP that provides basic terminal abilities like running commands, running Python, and working with files and folders.

An MCP server that wraps Apache Tika to extract text, metadata, and more from documents. It supports local files and optional remote URLs with SSRF protections.

Enables MCP clients to execute shell commands, manage long-running processes, and read/write files on the host machine with the permissions of the user running the server.

Enables AI clients to securely reach and control tools running on your own computers through a relay and outbound device agent.

Enables AI clients to read, write, search, and manage files in an Obsidian vault via MCP over SSE, running standalone without the Obsidian desktop app.

Exposes the local voidtools Everything index over MCP stdio on Windows, letting AI agents search, filter, aggregate, detect duplicates and grep file contents across millions of index entries in milliseconds instead of recursively scanning disks. It provides 13 tools and 3 resources, running loopback-only and read-only by default.

A modular framework for building and running multiple MCP servers with file operations, system information, and extensible tool/prompt/resource support.

Enables uploading images to a running PicGo application through its built-in server.

Enables AI agents to develop within a local project workspace by reading and modifying files, running commands and tests, checking Git state, and persisting progress as history sessions that can be restored in later conversations.

Enables local document Q&A by reading .txt or .pdf files and answering questions in Persian using locally running models.

Enables AI agents to run governed, auditable oncology data workflows through built-in tools for catalog listing, SQL queries, shell execution, file writes and exports, and approval status, with policy enforcement, approval gates, sandboxed execution, output redaction, and tamper-evident auditing.

An Obsidian plugin that runs an MCP server, enabling AI agents to read, edit, search notes, and run Dataview queries in your vault.

Enables MCP clients to read, write, append, delete, search, list, and inspect linked or active files in a local Obsidian vault, using a desktop bridge when Obsidian is running and a filesystem fallback otherwise.

Enables MCP clients such as Claude to search, tag, catalogue, ingest, audit, relocate, and repair a running Connecter asset library, including texture scanning and relinking, with dry-run plans and undoable journaled changes.

Enables ChatGPT conversations to drive a paired Windows PC by reading and writing files, running interactive terminals, automating desktop UI, and composing or editing DOCX documents in WordCraft, all through 42 MCP tools. Access is secured with OAuth, device pairing, approved folders, and locally managed permissions for sensitive actions.

Enables AI agents to search, read, create, update, and delete notes in an Obsidian vault over the Model Context Protocol, running either locally against vault files or in the cloud through an S3-synced bucket, with optional semantic search that turns the vault into always-available agent memory.

Enables AI harnesses such as ZCode and Claude Code to browse, search, edit, and create notes in an Obsidian vault through seven fine-grained tools over stdio. It works directly on the vault's filesystem without requiring Obsidian to be running, with built-in protections against accidental deletion or overwriting.

Exposes read-only local markdown envelopes through MCP tools for health, context, and recall queries.

Provides file system operations (read, search, list) and time queries, enabling Claude to interact with files and get time in any timezone.

A read-only MCP server that reports largest files, folder sizes, and disk usage, running locally without any data leaving your machine.

Enables AI tools to understand a database, inspect schema, and run safe SELECT queries with SQL guardrails, plus optional codebase reading.

Gives Claude and other MCP clients remote, authenticated read/write access to a personal Obsidian vault over HTTPS — reading and atomically writing markdown, parsing YAML frontmatter, running indexed frontmatter queries and full-text search — behind OAuth 2.0 login (or Cloudflare Access) and a Cloudflare Tunnel that never exposes the host directly to the internet.

Provides full read and write access to Excel workbooks (sheets, cell ranges, tables, formulas, formatting, and cross-workbook references) via MCP, running locally or as an HTTP/SSE service.

A local evidence recorder that captures screenshots, recordings, notes, and summaries during long-running agent tasks, enabling reviewable task records with timelines and artifacts.

Enables listing and running Ansible playbooks, managing roles, reading docs, and creating vars files for the jetlag project.

Enables ChatGPT to work on a local project by reading and editing files, running shell commands, keeping terminals and desktop sessions open, and splitting work across durable workers whose context persists between tasks. Long-running work can be steered mid-flight, tracked with Goal, and carried into fresh chats via Compact & Resume.