"How to play a sound notification when a task is completed" matching MCP servers:

MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.

Enables searching and retrieving content, module information, and Twig template snippets from a-blog cms via its GET API.

Enables AI assistants to query PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB databases through MCP with read-only, audited access.

Enables long-horizon autonomous task checkpointing and resumption through cryptographic event-sourced state persistence, idempotency key deduplication, timeout heartbeats, human-in-the-loop pause/resume tokens, and fail-safe recovery.

This MCP server lets AI agents connect to Figma to read, analyze, create, and modify designs, including elements, styles, assets, and code generation. It works with free Figma accounts and supports parallel multi-agent use across MCP-compatible clients.

AgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, attachments, search, crews, and agent runs.

Enables autonomous planning by decomposing prompts into directed acyclic task graphs and resolving dependency topologies for multi-agent pipelines.

Enables agents to transform tabular Markdown content into structured, type-inferred records with normalized formatting through an MCP-compatible interface.

Enables converting Markdown and HTML tables into structured JSON records with automatic column type inference and format normalization. It also offers supporting web-agent primitives such as DOM semantic pruning, form field auto-mapping, and execution trajectory evaluation, all via a zero-dependency MCP server.

Enables agents to break high-level business objectives into dependency-ordered sub-task graphs and then directly generate the finished deliverables, such as financial spreadsheets, executive presentations, and analytical reports. It runs as a zero-dependency Python MCP server over JSON-RPC stdio, adding deterministic authorization, role-boundary validation, and telemetry.

Thin MCP server that enables AI agents to generate video, image, and audio content via the Deepy API using a personal API key, with safe generation flow and no business logic.

Enables querying of a locally pinned snapshot of the Education-to-Workforce Indicator Framework — 99 indicators and 11.8M observations — to browse questions, describe metrics, resolve places, and fetch or rank data across national, state, county, and district levels.

Publishes static sites to Drop2Run from an AI agent: hand it files written in the chat or a folder on disk, and it returns a live HTTPS URL. Six tools — publish_files, publish_dir, list_sites, delete_site, and login / login_code — with no git, no build step and no repository.

Enables AI IDEs to interact with TaskMesh task management and time tracking APIs through secure, scoped access tokens.

Enables agents to discover available still-image animation models, obtain credit quotes without charge, submit one explicitly approved generation job, and poll the resulting short clip.

Enables Claude to query and manipulate GRID spreadsheets via the GRID API using natural language.

Enables searching government awards through the Sell to State API by proxying JSON-RPC to the live HTTP MCP endpoint, requiring an API key.

Lightweight project management for teams and AI agents.

Hourly electricity grid carbon intensity (gCO2eq/kWh) for 45 zones across Europe, the US and Great Britain, computed from ENTSO-E, EIA and NESO generation data. Four read-only tools; every value carries its interval timestamp and how stale it is. No API key, no account.

Metis gives AI agents expert know-how that named reviewers have approved, and only where its recorded conditions match the situation. High-risk situations go to a person. When an agent sees practice depart from procedure, it can send the expert one short question. Every retrieval is recorded on a hash-linked evidence chain.