"PostgreSQL MCP (Multi-Version Concurrency Control or specific usage)" matching MCP servers:

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

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.

Enables local-first document versioning with content-addressable storage, word-level AST diffs, and AI-compliance auditing for LLM agents.

Deterministic, LLM-first control of Word documents (.docx). An agent reads the outline, finds text by phrase, and applies edits as tracked changes and comments in one atomic batch, with a safety layer that refuses edits based on a stale read and rolls back failed batches. It works on .docx files directly, and can also drive an open document in Microsoft Word on Windows or in LibreOffice Writer.

Enables AI coding agents to retrieve the latest stable versions of packages and tools across multiple ecosystems, preventing outdated dependency versions in generated code.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

Turns Canvas LMS into a scriptable pipeline and exposes it to AI assistants via MCP for querying courses, grades, assignments, and syncing files using natural language.

Portable governance control-promotion CLI and MCP server.

A flexible proxy server that aggregates multiple backend MCP servers into a single interface using STDIO or SSE transports. It supports dynamic server management via an HTTP API and utilizes namespacing to prevent tool conflicts across connected services.

MCP server for managing multiple SSH servers via AI assistants, offering tools for remote command execution, file operations, and system monitoring.

Local MCP server that lets Claude Code delegate bounded, read-only tasks to external AI models (Codex, Grok, local OpenAI-compatible servers) via CLIProxyAPI.

An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.

Read-only MCP server for extracting data across multiple CallTrackingMetrics sub-accounts using a single parent API key. Enables cross-account call data, reports, numbers, contacts, and configuration analysis for resellers and agencies via Claude.

Enables AI assistants to control Roku TVs on the local network via natural language commands.

An MCP server that enables AI assistants to control TVs on a local network through natural language commands. It currently supports Roku devices, allowing users to launch apps, manage playback, and navigate menus.

Enables safe, structured control of Blender on Windows via a standalone STDIO MCP server, providing seven tools to inspect scenes, list and edit materials, transform objects, add modifiers, set smooth shading, and export assets without arbitrary code execution.

Manage local/SSH/WinRM remote hosts via MCP, providing tools for exec, filesystem, screen, process, serial console, and configuration.

MCP server that enables AI agents to read, edit, and create PLC projects in EcoStruxure Control Expert via COM automation.

Enables comprehensive Linux desktop agent capabilities for Ubuntu/Debian systems, including system state monitoring, package management, persistent terminal sessions, and desktop control via mouse, keyboard, and screen capture, with support for multiple remote machines and a built-in permission system.

Enables comprehensive Android device control over ADB, including UI automation, screen capture/recording, app management, file operations, and log/notification access, with a built-in permission system.