# Any Agent > A single interface to use and evaluate different agent frameworks - **Type:** MCP server - **Install:** `agentstack add mcp-mozilla-ai-any-agent` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [mozilla-ai](https://agentstack.voostack.com/s/mozilla-ai) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [mozilla-ai](https://github.com/mozilla-ai) - **Source:** https://github.com/mozilla-ai/any-agent - **Website:** https://docs.mozilla.ai/any-agent ## Install ```sh agentstack add mcp-mozilla-ai-any-agent ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # any-agent [](https://github.com/mozilla-ai/any-agent/actions/workflows/docs.yaml/) [](https://github.com/mozilla-ai/any-agent/actions/workflows/tests-integration.yaml/) [](https://pypi.org/project/any-agent/) A single interface to use and evaluate different agent frameworks. > [!IMPORTANT] > **`any-agent` is in soft deprecation.** It started as a research project to compare agent frameworks and refine a minimal common surface. That distillation has graduated to its own package: [`mozilla-ai-tinyagent`](https://github.com/mozilla-ai/tinyagent) (PyPI: `mozilla-ai-tinyagent`). For new projects we recommend using `tinyagent` directly. > > `any-agent` continues to be published and we'll take security/bug-fix PRs, but no new features are planned. Reach for `any-agent` when you specifically need to **run or evaluate agents across multiple frameworks** (Agno, Google ADK, LangChain, LlamaIndex, OpenAI Agents SDK, smolagents) under one API. If you only need the core agent loop, `mozilla-ai-tinyagent` is the leaner path. ## [Documentation](https://docs.mozilla.ai/any-agent/) - [Agents](https://docs.mozilla.ai/any-agent/agents/) - [Tools](https://docs.mozilla.ai/any-agent/agents/tools/) - [Tracing](https://docs.mozilla.ai/any-agent/core-concepts/tracing) - [Serving](https://docs.mozilla.ai/any-agent/core-concepts/serving) - [Evaluation](https://docs.mozilla.ai/any-agent/core-concepts/evaluation) ## [Supported Frameworks](https://docs.mozilla.ai/any-agent/) [](https://huggingface.co/blog/tiny-agents) [](https://github.com/google/adk-python) [](https://github.com/langchain-ai/langgraph) [](https://github.com/run-llama/llama_index) [](https://github.com/openai/openai-agents-python) [](https://github.com/huggingface/smolagents) [](https://github.com/agno-agi/agno) ### Planned for Support (Contributions Welcome!) [Open Github tickets for new frameworks](https://github.com/mozilla-ai/any-agent/issues?q=is%3Aissue%20state%3Aopen%20label%3Aframeworks) ## Requirements - Python 3.11 or newer ## Quickstart Refer to [pyproject.toml](./pyproject.toml) for a list of the options available. Update your pip install command to include the frameworks that you plan on using: ```bash pip install 'any-agent' ``` To define any agent system you will always use the same imports: ```python from any_agent import AgentConfig, AnyAgent ``` For this example we use a model hosted by Mistral, but you may need to set the relevant API key for whichever provider being used. See our [Model Configuration docs](https://docs.mozilla.ai/any-agent/agents/models/) for more information about configuring models. ```bash export MISTRAL_API_KEY="YOUR_KEY_HERE" # or OPENAI_API_KEY, etc ``` ```python from any_agent.tools import search_web, visit_webpage agent = AnyAgent.create( "tinyagent", # See all options in https://docs.mozilla.ai/any-agent/ AgentConfig( model_id="mistral:mistral-small-latest", instructions="Use the tools to find an answer", tools=[search_web, visit_webpage] ) ) agent_trace = agent.run("Which Agent Framework is the best??") print(agent_trace) ``` > [!TIP] > Multi-agent can be implemented [using Agents-As-Tools](https://docs.mozilla.ai/any-agent/agents/tools/#using-agents-as-tools). ## Cookbooks Get started quickly with these practical examples: - **[Creating your first agent](https://docs.mozilla.ai/any-agent/cookbook/your-first-agent)** - Build a simple agent with web search capabilities. - **[Creating your first agent evaluation](https://docs.mozilla.ai/any-agent/cookbook/your-first-agent-evaluation)** - Evaluate that simple web search agent using 3 different methods. - **[Using Callbacks](https://docs.mozilla.ai/any-agent/cookbook/callbacks)** - Implement and use custom callbacks. - **[Creating an agent with MCP](https://docs.mozilla.ai/any-agent/cookbook/mcp-agent)** - Integrate Model Context Protocol tools. - **[Serve an Agent with A2A](https://docs.mozilla.ai/any-agent/cookbook/serve-a2a)** - Deploy agents with Agent-to-Agent communication. - **[Building Multi-Agent Systems with A2A](https://docs.mozilla.ai/any-agent/cookbook/a2a-as-tool)** - Using an agent as a tool for another agent to interact with. ## Contributions The AI agent space is moving fast! If you see a new agentic framework that AnyAgent doesn't yet support, we would love for you to create a Github issue. We also welcome your support in development of additional features or functionality. ## Running in Jupyter Notebook If running in Jupyter Notebook you will need to add the following two lines before running AnyAgent, otherwise you may see the error `RuntimeError: This event loop is already running`. This is a known limitation of Jupyter Notebooks, see [Github Issue](https://github.com/jupyter/notebook/issues/3397#issuecomment-376803076) ```python import nest_asyncio nest_asyncio.apply() ``` ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [mozilla-ai](https://github.com/mozilla-ai) - **Source:** [mozilla-ai/any-agent](https://github.com/mozilla-ai/any-agent) - **License:** Apache-2.0 - **Homepage:** https://docs.mozilla.ai/any-agent Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-mozilla-ai-any-agent - Seller: https://agentstack.voostack.com/s/mozilla-ai - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.