# FindAgent documentation

FindAgent is the cross-LLM AI agent store. Discover focused AI agents and put them to work inside the LLM client you already use — Claude, ChatGPT, Gemini, Cursor, and more.

## What FindAgent is

Every agent on FindAgent is one package, published by a creator and ready to use in your LLM client. An agent is one package of up to four parts: Instructions, Skills, Actions and Code.

- **Instructions** — How the agent behaves: a prompt and example flows your AI app follows.
- **Skills** — Know-how your AI app loads when a task needs it, each skill served as a prompt.
- **Actions** — Calls to real tools with your own key, sent only to the hosts the agent declares.
- **Code** — A creator's own code from a GitHub repo, run in an isolated sandbox after review, or on your machine with your consent. [The Code part →](https://findagent.cloud/docs/code-agents)

Instructions, Skills and Actions run no code of their own; only the Code part does. Every agent page shows the parts it carries. Two things sit beside agents rather than inside them:

- **MCP servers** — An MCP server listing points at a server someone else runs; FindAgent lists it and never runs it. They live in the [MCP directory](https://findagent.cloud/mcp); new to the term? See [what an MCP server is](https://findagent.cloud/docs/what-is-an-mcp-server).
- **Departments** — A Department is two to sixteen agents (up to eight for peer-to-peer) composed into one team that runs as a single MCP server. It is not a plugin. [Departments →](https://findagent.cloud/docs/departments)

You browse the catalogue on two axes — **Industry** (the vertical an agent serves) and **Discipline** (the kind of work it does, like Customer Service or Software Development). Lead with whichever matches how you think, then intersect the two from the [Browse page](https://findagent.cloud/browse).

## What an agent's actions are

An agent with actions or skills declares **tools** in its manifest. Each tool describes what it does and how it is invoked (an HTTP call, a prompt template, or a call into another agent). A shared, trusted runtime executes those declared tools, so the catalogue stays safe to use while agents still do real work. See the [security model](https://findagent.cloud/docs/security) for why this matters.

## Two ways to use an agent

- **Connect.** Add the agent's gateway address in any MCP client and sign in once. Everything runs on FindAgent, with nothing to download. A hosted agent's address looks like **https://mcp.findagent.cloud/agents/<slug>**; it works from web and mobile clients too. [Connect guide →](https://findagent.cloud/docs/connect)
- **Install.** Add it as a plugin from the catalog, in apps that install plugins. Parts that run on your own machine are Install-only. [Install guide →](https://findagent.cloud/docs/install)

> **Which should I use?**
>
> Connect is the recommended path: it works in any client, including web and mobile, with nothing to maintain. Install only when your app installs plugins and you want the package's own files.

## Concepts

New to any of the words above? Each of these answers one question, in plain language:

- [What is an MCP server?](https://findagent.cloud/docs/what-is-an-mcp-server) — A plain-language definition of the Model Context Protocol and MCP servers, how they differ from a plugin or a raw API, and how they connect to Claude, ChatGPT, Gemini, and Cursor.
- [What is an AI agent?](https://findagent.cloud/docs/what-is-an-ai-agent) — What separates an agent from a chatbot or a prompt: tools, a goal, and the ability to take a multi-step action on your behalf.
- [What is an agent store?](https://findagent.cloud/docs/what-is-an-ai-agent-store) — How an agent store differs from a plugin directory or a prompt library, and what cross-LLM means for the agents you install.
- [What can agents do?](https://findagent.cloud/docs/what-can-ai-agents-do) — The real tasks agents with actions handle today — analysis, support triage, reporting, repo work — and where the honest limits are.
- [Cross-LLM, explained](https://findagent.cloud/docs/what-is-a-cross-llm-agent-store) — Why an agent that works in Claude should also work in ChatGPT, Gemini and Cursor, and what has to be true for that to hold.

## Go further

- Combine several agents into a team with an agent-to-agent topology and run them as one unit — see [Departments](https://findagent.cloud/docs/departments).
- Publishing your own agent? Start with the [creator guide](https://findagent.cloud/docs/creator-guide) and the [manifest spec](https://findagent.cloud/docs/manifest). You can even submit straight from your AI client — see [MCP & API](https://findagent.cloud/mcp-api).
- Looking for a remote MCP server? Browse the [MCP directory](https://findagent.cloud/mcp) and connect any listing to your client.
- Integrating programmatically? See the [API & integration](https://findagent.cloud/docs/api) reference.

[Browse the store](https://findagent.cloud/)