# SPREVA

> Connect the AI agent you already use, and ask it in plain words to draft, schedule, publish and report on your social media.

SPREVA speaks the Model Context Protocol (MCP), the open standard AI apps use to reach other software. Once connected, your agent works in your workspace the way you would: You never hand it an id. It names things the way you do, and every change goes through the same checks as the app.

Connector URLs: `https://dev-app.spreva.ai/api/mcp` (SPREVA, every tool) and `https://dev-app.spreva.ai/api/mcp/publishing` (SPREVA Publishing, without the Studio).

## Get started

- [SPREVA for AI agents](https://spreva.ai/docs): Set up SPREVA in ChatGPT, Claude, Cursor, Codex, Gemini and other AI agents: connector URLs, sign-in, tools, permissions and troubleshooting.
- [Quickstart](https://spreva.ai/docs/quickstart): Connect ChatGPT, Claude, Cursor or another AI agent to SPREVA in about a minute.
- [Ways to connect](https://spreva.ai/docs/connect): Connect an AI agent to SPREVA with a connector URL and sign-in, an API key, the CLI's stdio bridge, or the CLI and its Agent Skill.
- [Two connectors](https://spreva.ai/docs/connectors): SPREVA, with every tool, and SPREVA Publishing, without the Studio's video and image tools: their URLs and when to use each.

## AI Agents

- [AI agents](https://spreva.ai/docs/agents): Set up SPREVA in ChatGPT, Claude, Claude Code, Codex, Cursor, Gemini, OpenClaw, Hermes Agent and other AI agents.
- [ChatGPT](https://spreva.ai/docs/agents/chatgpt): OpenAI's assistant. It connects to SPREVA through developer mode, on the web.
- [Claude](https://spreva.ai/docs/agents/claude): Anthropic's assistant, on the web, on the desktop and on mobile.
- [Claude Cowork](https://spreva.ai/docs/agents/claude-cowork): Claude's way of working on longer tasks. Since September 2026, it is part of Claude itself.
- [Claude Code](https://spreva.ai/docs/agents/claude-code): Anthropic's coding agent, in the terminal, in your editor and in the Claude desktop app.
- [Codex](https://spreva.ai/docs/agents/codex): OpenAI's coding agent, in the terminal, in the IDE extension and in the ChatGPT desktop app.
- [Cursor](https://spreva.ai/docs/agents/cursor): The AI code editor, whose agent can use MCP tools.
- [Gemini](https://spreva.ai/docs/agents/gemini): Google's assistant, in the Gemini app, in Gemini CLI and in Antigravity.
- [OpenClaw](https://spreva.ai/docs/agents/openclaw): An open-source personal agent that runs on your own machine and answers in your chat apps.
- [Hermes Agent](https://spreva.ai/docs/agents/hermes): Nous Research's open-source agent, which keeps what it learns as skills.
- [Grok](https://spreva.ai/docs/agents/grok): xAI's assistant, on grok.com and in its apps.
- [Grok Build](https://spreva.ai/docs/agents/grok-build): xAI's coding agent for the terminal.
- [DeepSeek](https://spreva.ai/docs/agents/deepseek): DeepSeek's assistant, on the web and in its apps.
- [Kimi](https://spreva.ai/docs/agents/kimi): Moonshot AI's assistant. SPREVA connects through Kimi Code CLI, its agent for the terminal.
- [Muse](https://spreva.ai/docs/agents/muse): Meta's personal agent, and Muse Code, its coding agent for the terminal.
- [Perplexity Computer](https://spreva.ai/docs/agents/perplexity): Perplexity's agent, which carries out long tasks across the web and your connected apps.
- [NanoClaw](https://spreva.ai/docs/agents/nanoclaw): A small open-source personal agent that runs each group's work in its own container.
- [Paperclip](https://spreva.ai/docs/agents/paperclip): Open-source software for running a company of AI agents, with goals, budgets and reviews.
- [MCP Server](https://spreva.ai/docs/agents/mcp): Any app that speaks the Model Context Protocol.
- [AI Agents CLI](https://spreva.ai/docs/agents/cli): SPREVA's command line, for any agent that can run shell commands.

## Reference

- [Tools](https://spreva.ai/docs/tools): The tools SPREVA gives AI agents: what each one does, its risk level and which connector has it.
- [Permissions and safety](https://spreva.ai/docs/permissions): Risk levels, Allow, Ask first and Needs approval, previews and confirmations, revisions and request ids: how SPREVA keeps agents safe.
- [Troubleshooting](https://spreva.ai/docs/troubleshooting): Fix sign-in loops, plans without agent access, the rate limit, the wrong connector, things an agent can't find, and time zones.
- [CLI](https://spreva.ai/docs/cli): Install the spreva command line, give it an API key, and use SPREVA from a terminal, a script or an AI agent.
- [Agent Skill](https://spreva.ai/docs/skill): Install SPREVA's Agent Skill in Claude Code, Codex, OpenClaw, Hermes Agent and other agents that support skills.

## Optional

- [llms-full.txt](https://spreva.ai/llms-full.txt): every page above in one file.
- [skill.md](https://spreva.ai/skill.md): SPREVA's Agent Skill, to install in an agent that supports skills.
- [REST API](https://spreva.ai/developers): the REST API, webhooks and API keys.