A read-only Figma MCP server that lets Claude list frames, read a frame's layout as flexbox, extract color and text styles as CSS variables, export icons as SVG, and render a PNG of the frame for visual comparison. This gives Claude everything it needs to build a matching web page from a design on Figma's free plan, with responses cached locally.

Enables AI chat backends to fetch public webpages and obtain cleaned readable text, Markdown, article content, metadata, and summary-ready prompts through MCP tools.

Enables reading status, scripts, parameters, and logs from a monome norns and performing gated writes, screenshots, script control, and safe deploys over SSH, OSC, and the matron REPL. Writes are dry-run by default and require explicit live and confirm flags.

Enables AI clients to securely control Linux and WSL2 systems over Streamable HTTP with Bearer token authentication, supporting command execution, background jobs, file operations, Docker management, system inspection, and audit log access with safety confirmations and path protections.

Enables MCP clients to curate YouTube watch history and locally search selected transcripts using SQLite FTS5, ChromaDB embeddings, and reciprocal rank fusion, with tools to browse unindexed history and add videos.

Renders validated declarative scene specifications into MP4 videos inside disposable, network-disabled containers, then serves an embedded player with playback controls and diagnostics through MCP Apps. Users can iteratively revise scenes conversationally, with revision history preserved and identical renders reused per account.

Enables AI assistants to automate Microsoft Edge in IE mode through Selenium and IEDriver, letting them inspect legacy pages, fill forms, click controls, handle frames, alerts, windows, and file uploads.

Enables agents to retrieve permission-filtered document knowledge across organizations and knowledge bases, and to identify and expand business terms and typed object relationships through a unified MCP interface.

Enables AI assistants to search for real Iconify icons, check icon names and properties, retrieve version-matched pyside-iconify usage references, and statically validate pyside-iconify code before running it.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Enables MCP clients such as Codex and Claude to plan natural-language or timed actions, generate and revise skeletal motion locally through a Kimodo runtime, and review results with diagnostics, candidate comparison, and interactive 3D previews. Provides checked handoffs of verified exports into Blender and Unreal Engine.

Enables MCP clients to read exported WhatsApp school-group chats, surface events and doubtful amounts, dates, or times, check conflicts, and export confirmed events to an .ics calendar with reminders.

Enables MCP clients to retrieve mid-band account summaries, quarterly reviews, upgrade-path eligibility, and priority artifact access for a named-relationship retainer.

Enables users to compute symbolic derivatives and integrals, including definite and improper cases, and verify antiderivatives through SymPy-backed MCP tools.

Enables MCP-capable assistants such as Codex and Claude to delegate bounded text work — summaries, structured extraction, classification, rewrites, code drafts and log digestion — to locally hosted Ollama models, with conservative routing that keeps small or sensitive tasks with the caller and private-result artifacts for sensitive output.

Enables administering Ubuntu hosts through MCP over stdio, currently exposing a read-only get_system_info tool that reports OS release, hostname, kernel, architecture, memory, and root filesystem capacity.

Enables querying USDA FAS Export Sales Reporting data through read-only tools, including weekly export quantities by commodity, destination country and market year, latest-week and top-destination slices, data release dates, and lookups of commodity, country, region and unit codes. Cross-references ESR's own integer codes against packaged reference lists so valid commodities and destinations are resolved before any request.

Enables Claude to read and manage Apple Business API resources such as devices, device management services, users, groups, apps, blueprints, configurations, and audit events through OAuth 2 authentication. Write and destructive operations are gated behind flags and require a two-step preview-and-confirm flow, with guardrails and local audit logging.

Enables VS Code Copilot Chat and custom agents to perform MongoDB queries, writes, transactions, schema discovery, index and collection management, and administrative commands across multiple secure connection profiles without using mongosh or PowerShell.

Enables AI clients to extract transcripts from specific Douyin, Xiaohongshu, and YouTube links, or from local media and subtitle files, with tools to check readiness, run extraction, and read paginated transcripts.

Enables MCP clients to drive a separately installed OrcaSlicer instance through a local stdio server, covering slicing jobs, profile and 3MF/settings editing, raw CLI options, artifact inspection and an optional desktop adapter for GUI actions. It also provides job queuing, status tracking and runtime detection of the installed binary's capabilities.

Enables MCP-compatible clients to plan, validate, generate, and deploy complete network topologies from natural-language instructions, including live deployment to a running network simulator and export to configuration or script files.

Exposes an OSINT investigation toolkit to any MCP-compatible AI client, which can drive passive checks such as DNS, WHOIS/RDAP, breach, IP reputation, GitHub and news-geo lookups and chain findings across them. The server lists 20 tools by default (16 passive plus 4 graph and batch helpers) and 25 when active checks are explicitly allowed, running via uvx with no separate install.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.