@@ -974,7 +974,8 @@ You can use mcp-agent applications in a standalone fashion (i.e. they aren't par
### How do I deploy to Cloud?
-Run `uvx mcp-agent deploy ` after logging in with `uvx mcp-agent login`. The CLI packages your project, provisions secrets, and exposes an MCP endpoint backed by a durable Temporal runtime. See the [Cloud quickstart](https://docs.mcp-agent.com/get-started/deploy-to-cloud) for step-by-step screenshots and CLI output.
+Run `uvx mcp-agent deploy ` after logging in with `uvx mcp-agent login`. The CLI packages your project, provisions secrets, and exposes an MCP endpoint backed by a durable Temporal runtime. See the [Cloud quickstart](https://docs.mcp-agent.com/get-started/
+ cloud) for step-by-step screenshots and CLI output.
### Where is the API reference?
diff --git a/docs/docs.json b/docs/docs.json
index bebda503f..986bedb2d 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -35,7 +35,7 @@
"get-started/welcome",
"get-started/quickstart",
"get-started/install",
- "get-started/deploy-to-cloud"
+ "get-started/cloud"
]
},
{
diff --git a/docs/get-started/deploy-to-cloud.mdx b/docs/get-started/cloud.mdx
similarity index 59%
rename from docs/get-started/deploy-to-cloud.mdx
rename to docs/get-started/cloud.mdx
index 3e9d1b0d6..fd6aff700 100644
--- a/docs/get-started/deploy-to-cloud.mdx
+++ b/docs/get-started/cloud.mdx
@@ -1,7 +1,7 @@
---
-title: Deploy to Cloud
-sidebarTitle: "Deploy to Cloud"
-description: "Publish your agent to the Cloud with the CLI."
+title: "MCP-Cloud (mcp-c)"
+sidebarTitle: "Cloud"
+description: "Deploy and host your mcp-agents and apps on the cloud."
icon: cloud
---
@@ -9,32 +9,30 @@ icon: cloud
`mcp-c` is in open beta, and free to use. Share feedback via [GitHub issues](https://github.com/lastmile-ai/mcp-agent/issues) or [Discord](https://lmai.link/discord/mcp-agent).
-## What is mcp-c?
+## What is MCP-Cloud?
-Before diving into the workflow, here is the 30‑second summary. See the dedicated pages under [Deployment](/cloud/overview) for full detail:
+MCP-Cloud (mcp-c) is a fully managed cloud platform for hosting mcp-agents, apps, and mcp servers.
-- **One runtime for any MCP application** – deploy durable `mcp-agent` workflows, FastMCP servers, or ChatGPT App backends. Everything is exposed as an MCP server at `https://.deployments.mcp-agent.com` ([Cloud overview](/cloud/mcp-agent-cloud/overview)).
+
+
+### Key Benefits
+
+- **One runtime for any MCP application** – deploy durable `mcp-agent` workflows, FastMCP servers, or ChatGPT App backends. Everything is exposed as an MCP server at `https://.deployments.mcp-agent.com` ([Cloud overview](/cloud/mcp-agent-cloud/overview)).
- **Temporal-backed execution** – long-running tools and workflows run on Temporal with retries, pause/resume, and human input support ([Long-running tools](/cloud/mcp-agent-cloud/long-running-tools)).
-- **Managed secrets & authentication** – classify secrets during deploy, collect user secrets later, and choose bearer or unauthenticated access today (OAuth coming soon) ([Manage secrets](/cloud/mcp-agent-cloud/manage-secrets) and [Deployment auth](/cloud/authentication/deployment-auth)).
+- **Managed secrets & authentication** – manage secrets for both you, as the developer, and your users. Allow users to specify their own keys, and choose bearer or unauthenticated access today (OAuth coming soon) ([Manage secrets](/cloud/mcp-agent-cloud/manage-secrets) and [Deployment auth](/cloud/authentication/deployment-auth)).
- **Observability built in** – stream logs, forward traces, and inspect workflow history directly from the CLI ([Observability](/cloud/observability)).
- **Easy client install** – use `mcp-agent install` or `mcp-agent cloud configure` to wire the deployed server into Claude Desktop, Cursor, VS Code, or ChatGPT Apps ([Use a deployed server](/cloud/mcp-agent-cloud/use-deployed-server)).
With that context, the steps below show exactly how to deploy.
-## TL;DR – three commands
-
-```bash
-uvx mcp-agent login
-uvx mcp-agent deploy my-agent
-uvx mcp-agent cloud servers list
-uvx mcp-agent cloud servers describe my-agent
-```
-
-1. `login` stores your API token locally.
-2. `deploy` packages the current directory and uploads it.
-3. `cloud servers list` shows every deployment you have access to.
-4. `cloud servers describe` confirms the deployment URL and secret policy.
-
## 1. Authenticate
```bash
@@ -51,7 +49,7 @@ From the directory containing your `mcp_agent.config.yaml` (or pass `--config-di
uvx mcp-agent deploy my-agent
```
-During deployment you'll classify secrets as **deployment** (stored securely) or **user** (provided later via `mcp-agent cloud configure`). Use `--dry-run` to validate without uploading or `--non-interactive` for CI.
+During deployment you'll classify secrets as **deployment** (stored securely) or **user** (provided later via `mcp-agent cloud configure`).
```bash basic
@@ -61,14 +59,14 @@ directory/
└── mcp_agent.secrets.yaml
```
```bash deploy
-uvx mcp-agent deploy my-agent --dry-run
+uvx mcp-agent deploy my-agent
```
After a successful deploy you'll receive an endpoint like:
```
-https://.deployments.mcp-agent.com
+https://.deployments.mcp-agent.com
```
## 3. Connect from clients
@@ -78,13 +76,12 @@ Your cloud deployment is a standard MCP server. Use any MCP client:
```bash
- uvx mcp-agent install https://.deployments.mcp-agent.com \
+ uvx mcp-agent install https://.deployments.mcp-agent.com \
--client claude_desktop \
- --name research-buddy \
- --dry-run
+ --name research-buddy
```
- Replace `claude_desktop` with `vscode`, `cursor`, `chatgpt` to install in those clients instead.
+ Replace `claude_desktop` with `vscode`, `cursor`, `chatgpt`, `claude_code` to install in those clients instead.
@@ -95,7 +92,7 @@ Your cloud deployment is a standard MCP server. Use any MCP client:
servers:
my_agent_cloud:
transport: sse
- url: "https://.deployments.mcp-agent.com/sse"
+ url: "https://.deployments.mcp-agent.com/sse"
headers:
Authorization: "Bearer ${MCP_API_KEY}"
```
@@ -142,39 +139,60 @@ Your cloud deployment is a standard MCP server. Use any MCP client:
-## Example: web summarizer workflow
+## Example: 👋 Hello World agent
```python main.py
import asyncio
+from typing import Optional
+
from mcp_agent.app import MCPApp
from mcp_agent.agents.agent import Agent
-from mcp_agent.executor.workflow import Workflow, WorkflowResult
+from mcp_agent.core.context import Context as AppContext
from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM
-app = MCPApp(name="web_summarizer")
-
-@app.workflow
-class WebSummarizerWorkflow(Workflow[str]):
- @app.workflow_run
- async def run(self, url: str) -> WorkflowResult[str]:
- agent = Agent(
- name="summarizer",
- instruction="Fetch and summarize web content concisely.",
- server_names=["fetch"],
+# Create the MCPApp, the root of mcp-agent.
+app = MCPApp(name="hello_world", description="Hello world mcp-agent application")
+
+# Hello world agent: an Agent using MCP servers + LLM
+@app.tool()
+async def finder_agent(request: str, app_ctx: Optional[AppContext] = None) -> str:
+ """
+ Run an Agent with access to MCP servers (fetch + filesystem) to handle
+ the input request.
+ """
+ agent = Agent(
+ name="finder",
+ instruction=(
+ """You are a helpful assistant. Use MCP servers to fetch and read
+ files, then answer the request concisely."""
+ ),
+ server_names=["fetch", "filesystem"],
+ context=app_ctx,
+ )
+
+ async with agent:
+ llm = await agent.attach_llm(OpenAIAugmentedLLM)
+ result = await llm.generate_str(message=request)
+ return result
+
+async def main():
+ async with app.run() as agent_app:
+ # Run the agent
+ readme_summary = await finder_agent(
+ request="Please summarize the README.md file in this directory.",
+ app_ctx=agent_app.context,
)
+ print(readme_summary)
+
- async with agent:
- llm = await agent.attach_llm(OpenAIAugmentedLLM)
- summary = await llm.generate_str(
- f"Fetch {url} and provide a 3-sentence summary"
- )
- return WorkflowResult(value=summary)
+if __name__ == "__main__":
+ asyncio.run(main())
```
Deploy with:
```bash
-uvx mcp-agent deploy web-summarizer
+uvx mcp-agent deploy hello-world
```
## Learn more
diff --git a/docs/get-started/install.mdx b/docs/get-started/install.mdx
index a2494e960..bf405bc3f 100644
--- a/docs/get-started/install.mdx
+++ b/docs/get-started/install.mdx
@@ -130,5 +130,5 @@ mcp-agent includes optional extras for different LLM providers. Install the ones
## Next steps
- [Quickstart](/get-started/quickstart) – create a finder agent and run it locally.
-- [Deploy to Cloud](/get-started/deploy-to-cloud) – publish your agent with `uvx mcp-agent deploy`.
+- [Deploy to Cloud](/get-started/cloud) – publish your agent with `uvx mcp-agent deploy`.
- [MCP Servers](/mcp-agent-sdk/mcp/overview) – learn how FastMCP and other servers plug into your agents.
diff --git a/docs/get-started/quickstart.mdx b/docs/get-started/quickstart.mdx
index 9b08a9f1a..32476a14d 100644
--- a/docs/get-started/quickstart.mdx
+++ b/docs/get-started/quickstart.mdx
@@ -23,11 +23,18 @@ Let's get you set up with a hello world mcp-agent!
```bash
uvx mcp-agent init
uv init
- uv add mcp-agent
+ uv add "mcp-agent[openai]"
uv sync
```
(Prefer pip? `python -m venv .venv && pip install mcp-agent` works too.)
+
+ In the `mcp_agent.secrets.yaml` in your project directory, add your OpenAI or other model provider key.
+ ```yaml mcp_agent.secrets.yaml
+ openai:
+ api_key: "your-openai-api-key"
+ ```
+
@@ -42,7 +49,7 @@ Let's get you set up with a hello world mcp-agent!
```bash
uv init
- uv add mcp-agent
+ uv add "mcp-agent[openai]"
uv sync
```
@@ -51,7 +58,7 @@ Let's get you set up with a hello world mcp-agent!
`mcp_agent.config.yaml`
- ```yaml
+ ```yaml mcp_agent.config.yaml
execution_engine: asyncio
logger:
transports: [console]
@@ -71,7 +78,7 @@ Let's get you set up with a hello world mcp-agent!
```
`mcp_agent.secrets.yaml`
- ```yaml
+ ```yaml mcp_agent.secrets.yaml
openai:
api_key: "your-openai-api-key"
```
@@ -79,7 +86,7 @@ Let's get you set up with a hello world mcp-agent!
`main.py`
- ```python
+ ```python main.py
import asyncio
import os
import time
@@ -158,4 +165,4 @@ uvx mcp-agent deploy
- Check out the generated README (if you used the CLI) for tips on extending the agent.
- Layer in more capabilities using the [Effective Patterns](/mcp-agent-sdk/effective-patterns/overview) guide.
-- Ready to deploy your agent? Follow [Deploy to Cloud](/get-started/deploy-to-cloud).
+- Ready to deploy your agent? Follow [Deploy to Cloud](/get-started/cloud).
diff --git a/docs/get-started/welcome.mdx b/docs/get-started/welcome.mdx
index aafc3ad76..aa98a0e98 100644
--- a/docs/get-started/welcome.mdx
+++ b/docs/get-started/welcome.mdx
@@ -76,7 +76,7 @@ if __name__ == "__main__":
Use `uvx mcp-agent deploy` to host your agent as a managed MCP server.