Enables coding agents to work inside a live WordPress Elementor editor tab: reading the canvas skeleton and element settings, creating/updating/moving/deleting elements through Elementor's own command API as single undo steps, taking pixel-accurate screenshots, running design lint, and receiving prompts the user types in the editor with Alt+Space. A ghost cursor and overlay let you follow along, and nothing touches the database directly.
Enables AI assistants to analyze code repositories and generate self-contained interactive HTML5/SVG architecture diagrams from project structure or existing Mermaid diagrams, fully air-gapped with no external dependencies.
Enables AI hosts to generate and open Mermaid diagram links in Markdown files, providing tools for syncing, listing, and injecting diagrams via the Mermaid.ai editor.
An AI music production and mixing partner for Ableton Live via MCP. Program expressive MIDI clips, design synth parameters, shape automation curves, arrange on the timeline, and mix tracks with real-time verified feedback.
Enables AI agents to operate a real-time DJ rig inside Ableton Live, controlling two decks, bar-quantized firing, crossfades, performance FX macros, and a harmonic crate that suggests next tracks by BPM and Camelot key.
Interactive, streaming SSH tool for LLM agents that enables spawning long-running remote commands with live line-by-line output, signal handling, stdin input, and SFTP file transfer.
Provides tools for editing an already-open PowerPoint presentation in real time, including slide, shape, text, formatting, note, comment, and export operations, without launching a separate PowerPoint instance.
Attaches to already-open Excel workbooks on Windows via COM to enable live editing of cells, ranges, formatting, and comments, without launching or closing Excel itself.
Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.
Enables multi-agent council workflows for coding assistants, providing parallel independent reviews, plans, brainstorms, validation, and research with strict read-only boundaries.
An MCP proxy that embeds tool definitions and returns only the top-k semantically relevant tools per query, reducing context usage and routing calls to upstream MCP servers.
An MCP server that enables AI agents to pause and request human approval or information via Slack, Telegram, or macOS dialogs before proceeding with actions.
Wraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.
Enables MCP clients to query the ransomware.live PRO threat-intelligence API through 25 read-only tools covering ransomware group TTPs, victims, IOCs, YARA rules, ransom notes, leaked negotiation chats, press coverage, SEC 8-K disclosures, and CSIRT contacts.
Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.
Enables real-time transcription and heuristic vocal stress analysis of live financial webcasts, providing an LLM with rolling transcripts and a stress score.
Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.
Provides structural, queryable understanding of a Python codebase via MCP tools, enabling direct lookups for callers, dependencies, and class hierarchies without repeated grep/read cycles.
Serves bundled local engineering guidance—four instructions, a control Guide and 20 software engineering procedures—over local STDIO so coding agents can discover and read the right procedure for a task. It is read-only and stateless, leaving all project changes and permissions to the consuming agent.