"Kit" matching MCP servers:

Enables AI assistants and local workflows to run Jev-powered tools that judge speeches line by line, audit drafts against goals, bisect hard-to-test bugs, simulate common-sense physics, score note pairs, and ask arbitrary typed questions cheaply.

Enables Codex to delegate tasks to ChatGPT through a browser-backed Oracle connection, with project memory and a verified-result cache. It supports preview, delegation, result polling, and explicit acceptance without an API fallback.

Enables coding agents to run source-bound evidence checks and bounded batch judgments for classification, extraction, and decision tasks via TypeSafe Jev.

Enables generating images from prompts and synthesizing speech from text using Cloudflare Workers AI, returning outputs through short-lived presigned links.

Enables AI assistants to perform typed decisions (choice, score, noul) over text, emails, tickets, or JSON documents, with automatic language routing and source ranking across 100+ languages via a single forward pass.

Enables authorized clients to invoke tenant-aware conversational assistant tools and resources over MCP, including durable conversations, agent configuration, connector policies, and PostgreSQL-backed data.

Provider-neutral short-form AI video toolkit for agents: Sora, Gemini Veo, xAI/Grok and Seedance.

An MCP server built into a Next.js app that serves prompts via the Model Context Protocol, supporting local and cloud LLM providers.

Connect AI assistants to Unfold It -- create goals with AI-generated plans, agent-assisted clarification, plan import with enrichment, individual progress tracking, cohort analytics, and skill assessments.

A multi-agent literature review pipeline that uses specialized agents to research, peer-review, and synthesize academic and practitioner perspectives into grounded reports.

Enables image generation using KIE.ai models like google/nano-banana and GPT Image 2. Supports asynchronous single or parallel image generation and file uploading for image inputs.

Enables AI coding agents to check whether engines like ChatGPT, Claude, Perplexity, Gemini and Grok recommend a given product: it starts an AI-visibility report, polls it, and reads back each engine's 'named in n of m answers', the competitors recommended instead, the cited sources, and a prioritised fix list. Also exposes free public AI rankings, suggested buyer questions, and distribution-kit generation.

MCP server for kie.ai providing image, video, and music generation with cost estimation, spending limits, and a transaction ledger.

Exposes SwarmLabs physics-informed scientific experiment predictions as MCP tools, enabling agents to run predictions, list engines, and perform parameter sweeps with honesty-first uncertainty reporting.

MCP server that enables generating songs or instrumental music using Suno V6, V6_MINI, and V6_WILD models via the Kie.ai API, with support for checking task status and retrieving audio URLs.

Lets AI agents drive a live, persistent Isaac Sim session: load any articulated robot from a USD plus JSON config, set normalized joint targets and named poses, tune gains and couplings live, run joint range tests, and capture screenshots. It also launches and monitors detached Isaac Lab training runs, with Kit kept up between calls so each experiment costs a frame instead of a full relaunch.

Enables coding agents to make offline, zero-cost decisions using schema-safe Choice/Score/Noul primitives, a confidence gatekeeper, planning, adversarial red-teaming, research, and RLVR-based self-improvement via 21 MCP tools.

Enables AI-assisted music creation and management with Suno V6 via Kie.ai, offering generation, extension, cover creation, persona handling, and download tools through a zero-dependency stdio JSON-RPC interface.

Enables AI agents to publish, claim, submit, and settle tasks with each other, including automatic decomposition of complex work into subtasks assigned to specialized agents. Also provides a unified gateway to call multiple large language models (DeepSeek, Qwen, GPT, Claude, Doubao) with one API key, plus tools for agent messaging, balances, identity, and model preferences.

A comprehensive Model Context Protocol server for the kie.ai generation API, providing access to 47+ image models, 86+ video models, and 20+ audio tools with deep model intelligence.