Ensemble testing for front-end web quality

Enables retrieval and structural analysis of FDA regulations.gov dockets: searching dockets, pulling comments and attachments into a local cache, extracting sectioned guidance text, and computing section-aligned draft-versus-final guidance diffs. All results are deterministic and cache-first, with no model calls in the server.

Enables creating, editing, previewing, and publishing hosted business websites with owner-approved OAuth access, including template discovery, image uploads, revision checks, and live publication status checks.

Enables AI agents to load web pages in true-to-size iPhone, iPad, and Android device frames, capture screenshots, inspect interactive elements and layout diagnostics, and automate tap/type/scroll flows with network mocks, console errors, and test evidence.

A local MCP server that places a safety layer between AI coding agents and Postgres, parsing every statement, holding risky or large writes for human approval, and journaling all activity on your machine. It enables one-command undo of individual agent-made changes and blocks destructive operations outright.

Enables AI assistants to access a user's Pusan National University Moodle-based LMS account, browsing courses, materials, notices, assignments, grades, calendars, and Q&A, downloading course files, and performing write actions like submitting assignments after a confirmation preview. It combines the official Moodle Web Service API with authenticated session scraping for the ubboard notice/Q&A boards.

Enables MCP-capable agents to settle deadlocks with a neutral, unsteerable tie-break and to obtain sealed independent AI review of their output, returning Ed25519-signed receipts that can be verified offline. Also supports running free demo matches and listing saved receipts with spend tracking.

Enables searching, filtering, and comparing custom plush manufacturers by country, MOQ, lead times, certifications, design inputs, and OEM/ODM capabilities, plus drafting RFQs for shortlisted suppliers. It serves bundled facts-only manufacturer data over stdio with no API key or network calls.

Enables MCP-compatible clients to send prompts or conversations to Chinese LLM models, list available models with pricing, and compare responses from multiple models through an OpenAI-compatible API.

Enables MCP clients to teach on a view-only local browser chalkboard by drawing equations, plots, molecules, diagrams, and science illustrations step by step, with snapshots and saved lessons.

Enables users to turn product links into TikTok and Reels post batches, including hooks, slide text, captions, hashtags, and render links, and to read profile credits and existing batches without spending credits, unlocking, or posting.

Enables comparison of supplied supplier or vendor statement open items against an accounts payable ledger, identifying missing items, amount and date discrepancies, and ambiguous repeated references with exact reference evidence.

Enables AI assistants to search and retrieve Phuket activities for a specific travel party in one tool call, returning diverse, safety-gated recommendations with live weather and sea context plus affiliate booking links.

It enables compatible AI agents to audit public web pages, crawl bounded same-host site samples, collect and compare AI answers, and read a user's own Google Search Console data locally.

Enables AI assistants to manage a social media calendar by listing connected channels, checking network rules, drafting, scheduling, or publishing posts, reviewing scheduled content, adjusting pending post settings, and importing or generating media.

Enables AI assistants to control and query a smart-home platform through natural language, including device services, states, automations, scripts, dashboards, history, and system management.

Enables coding agents to audit projects locally for token waste, calculate model arbitrage and pricing alternatives, and make request bodies cache-friendly, with payload optimization sending the supplied request body to the TokenZero service.

Enables AI agents to request Jupiter swap quotes, build unsigned Solana swap transactions for user signing, and access paid token-risk and wallet-portfolio data via x402.

Enables an AI agent to set up, run and verify engineering simulations through typed tools — creating or importing cases, setting boundary conditions, running solvers, checking convergence, verifying results against references, and rendering output, with edits appearing live in the GUI. It exposes no shell or code-execution tool.

Enables AI agents to see compiled LaTeX output: it builds the document, returns rendered page images, maps any point on a page back to its exact source line, and diffs what the last edit changed. It also audits an entire book for regressions, letting an agent diagnose and verify layout fixes without reading source alone.

Enables auditing MCP configuration token usage, compressing tool catalogs, pruning bloated JSON responses, and optionally persisting compressed profiles under read-only defaults and safety guardrails.

Enables clients to look up Pokémon stats, abilities, and type matchups, generate seeded random teams, analyze Showdown-style team text, and calculate simplified damage estimates using bundled offline data. It runs over stdio without API keys or runtime network requests.

Enables agents to submit authorized state bundles for free staging dry-run previews that deterministically consolidate memories, plans, tool schemas, and logs over MCP, reporting what stays active, what moves to archive, and why.

Enables MCP-capable AI apps to query a user's own Garmin sleep, HRV, stress, Body Battery, heart-rate, activity, and body-metric data through Garmin's official Personal API in a read-only, locally run setup.