A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

Agentic intelligence framework for Claude Code and Antigravity: slash commands, subagents, skills, hooks, governance, memory, and cost-aware model routing for AI-driven development.

An official Qdrant Model Context Protocol (MCP) server implementation

Enables agents to generate, refine, save, validate, and read sanitized SVG assets from text prompts through a local OpenAI-compatible model, with tools for listing and managing SVG files.

Enables MCP-compatible AI agents to interact with Discord through a local Vencord plugin inside the native desktop client, providing over 30 tools for messaging, server management, roles, moderation, and invites without bot or user tokens in config files.

Lets Claude and other MCP clients hand coding tasks to the Codex CLI as a sub-agent, running under the user's own Codex configuration so any configured model provider (OpenAI, DeepSeek, local models) does the work. Provides tools to start, poll, cancel and inspect jobs with compact change summaries, long-task handling, token-saving lean mode and clean process teardown.

Drives the local Doubao desktop client through its DevTools interface, letting an agent read and send chats, run task-mode work, hand off a project directory and take it back, and call Doubao-only capabilities like image generation and step traces. Also borrows Doubao's built-in skill set for cross-checking and project handoff, with a UI badge showing which side currently owns the work.

Enables agents to scan course structures, play videos at real 1x speed, track document task completion, capture quiz screenshots for vision-model reading, select and submit answers, and verify scores through MCP tools.

Enables listing models and running non-streaming chat completions against RelayRouter's OpenAI-compatible API, so agents can discover available models and send chat requests through a key-configured MCP endpoint.

Enables coding agents to propose, review, promote, and verify architecture changes as recorded C4 model updates, with hypothetical diffs, evidence-based qualification, and component histories.

Exposes 16 local stdio MCP tools that give Codex-style clients project-isolated persistent memory, local ONNX-based semantic search, and durable task tracking that survives across sessions and concurrent clients, without executing agents, hosting a model, or contacting model providers.

Enables MCP hosts to spawn, supervise, and collect results from parallel panels of pinned-model OpenCode v2 agents for delegated tasks, reviews, and cross-model comparisons. Supports per-member roles, models, permissions, follow-up prompts, cancellation, and persisted result retrieval.

Enables AI agents to debug Commodore software in a locally running VICE emulator through its text remote monitor, inspecting registers, memory and screens, disassembling code, setting breakpoints and watchpoints, controlling execution, and working with disk images, snapshots and exported graphics. Runs locally over stdio and includes safety guidance for state-changing operations.

This MCP server enables agents to administer a self-hosted AI control plane for users, organizations, subscriptions, API keys, model providers, and service health, with local-first model routing and cloud failover.

Embeds a runtime MCP inspector in a NestJS app so coding agents can inspect the module and provider graph, routes and their guards/interceptors/pipes/filters, logs, request traces, event listeners, and scheduled jobs through an HTTP endpoint.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Frontier model solution tracing, then made the prompting skills so Sonnet, GPT, DeepSeek, GLM, Kimi, ETC models work like that

Enables AI agents to run private web searches against a self-hosted SearXNG instance, rerank results with a local model, and fetch or extract pages locally into markdown, including PDFs, with optional caching, crawling, and cited local-LLM answers.

Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.

Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawning and waiting on agents, sending follow-ups, and aborting, backed by a live local web panel showing status, token usage, and streaming output.

Mounts a headless, low-memory browser for agents with a text-first tool interface, enabling navigation, semantic tree/markdown extraction, structured-data scraping, screenshots, form interaction, and session capture. Reads and interactions are returned as semantic trees, markdown, or CSS-selector JSON rather than pixels, which is cheaper for a model to reason over.

Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀

Enables agents and terminal users to browse MongoDB databases and collections, run queries and aggregation pipelines, modify documents, manage indexes and collections, inspect statistics and logs, and explain query plans.

Enables agents and terminal users to inspect ClickHouse over HTTP by listing databases and tables and running guarded read-only SELECT queries without modifying data.