From 0c7811578f85d790bfd760be01f3e0de85a71e94 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 15:43:24 -0400 Subject: [PATCH 01/12] Updating docs.mcp-agent.com homepage - updating quick start code snippet - adding hyperlinks for examples --- docs/index.mdx | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/docs/index.mdx b/docs/index.mdx index f6dd03381..8b88e1ea6 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -22,6 +22,7 @@ The framework handles: - Connect to any MCP server via stdio, SSE, WebSocket, or HTTP - Access tools, resources, prompts, and file system roots - Automatic tool discovery and integration +- Sampling, elicitation, and notifications ### Agent Patterns Implementation of all patterns from Anthropic's research: @@ -48,7 +49,7 @@ Works with: ## Quick Example -```python +```python main.py import asyncio from mcp_agent.app import MCPApp from mcp_agent.agents.agent import Agent @@ -56,8 +57,14 @@ from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM app = MCPApp(name="example_agent") -async def main(): +@app.tool +async def research()->str: + ''' + Research quatum computing function / tool call + ''' + result="" async with app.run() as mcp_agent_app: + # Create agent with MCP server access agent = Agent( name="researcher", @@ -76,9 +83,10 @@ async def main(): # Agent can now use MCP server tools result = await llm.generate_str("Research quantum computing") print(result) + return result if __name__ == "__main__": - asyncio.run(main()) + asyncio.run(research()) ``` ## Example Applications @@ -135,7 +143,7 @@ uv add "mcp-agent[openai,anthropic,azure,bedrock,google]" mcp-agent uses two configuration files: **mcp_agent.config.yaml** - Application configuration: -```yaml +```yaml mcp_agent.config.yaml execution_engine: asyncio # or temporal logger: transports: [console] @@ -155,7 +163,7 @@ openai: ``` **mcp_agent.secrets.yaml** - API keys and secrets: -```yaml +```yaml mcp_agent.secrets.yaml openai: api_key: "sk-..." ``` @@ -175,14 +183,14 @@ your-project/ ### Local Development Run agents locally with asyncio execution engine for rapid development. -### Production with Temporal +### [Production with Temporal](advanced/temporal) Use Temporal for durable execution, automatic retries, and workflow management. -### As MCP Server +### [As a MCP Server](cloud/agent-server) Expose your agents as MCP servers that can be used by Claude Desktop, VS Code, or other MCP clients. -### MCP Agent Cloud -Deploy agents to managed cloud infrastructure with one command (coming soon). +### [MCP Agent Cloud](cloud/overview) +Deploy agents to managed cloud infrastructure with one command. ## Examples @@ -206,4 +214,4 @@ The [examples directory](https://github.com/lastmile-ai/mcp-agent/tree/main/exam - [Model Context Protocol](https://modelcontextprotocol.io) - MCP specification - [Building Effective Agents](https://www.anthropic.com/research/building-effective-agents) - Anthropic's guide - [GitHub Repository](https://github.com/lastmile-ai/mcp-agent) - Source code -- [Discord Community](https://lmai.link/discord/mcp-agent) - Get help and discuss \ No newline at end of file +- [Discord Community](https://lmai.link/discord/mcp-agent) - Get help and discuss From a1430ea609664d17372ed2ccc1595435c2b57dff Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 16:28:30 -0400 Subject: [PATCH 02/12] Reducing example videos, updating static cover screenshot to video --- docs/index.mdx | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/docs/index.mdx b/docs/index.mdx index 8b88e1ea6..e3941f84c 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -3,7 +3,10 @@ title: Introduction description: "Framework for building AI agents using Model Context Protocol" --- -Agent execution example + ## Overview @@ -90,22 +93,6 @@ if __name__ == "__main__": ``` ## Example Applications - -### Agent as MCP Server Demo - - -### Workflow Orchestration -Orchestrator workflow visualization - -### Swarm Intelligence Pattern - - Explore working examples in the [examples directory](https://github.com/lastmile-ai/mcp-agent/tree/main/examples): - **Agent as MCP Server**: Deploy agents as MCP servers for Claude Desktop integration ([examples/mcp_agent_server](https://github.com/lastmile-ai/mcp-agent/tree/main/examples/mcp_agent_server)) From 627907653c10069afca5b8e4cca2006931ab1244 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 16:52:58 -0400 Subject: [PATCH 03/12] Updating cloud secrets management --- docs/configuration.mdx | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/docs/configuration.mdx b/docs/configuration.mdx index e1a08b562..213d7ebf2 100644 --- a/docs/configuration.mdx +++ b/docs/configuration.mdx @@ -692,13 +692,14 @@ Keep sensitive configuration in separate secrets files: - For cloud deployments, use secret management services: + For mcp-agent cloud deployments, use mcp-agent cloud's secret management: ```yaml - # Reference secrets from cloud providers openai: - api_key: "${OPENAI_API_KEY}" # From AWS Secrets Manager, etc. + api_key: !developer_secret ``` + + Mark which secrets you, as the developer, want to keep safe and secure.s @@ -1269,4 +1270,4 @@ usage_telemetry: UsageTelemetrySettings See real configuration examples - \ No newline at end of file + From 459a4aff156cf7ea85c6e929508af6c110cf3e02 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 16:56:56 -0400 Subject: [PATCH 04/12] Updating MCP Primitive Support Matrix with Sampling --- docs/concepts/mcp-primitives.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/concepts/mcp-primitives.mdx b/docs/concepts/mcp-primitives.mdx index 1b2f151d1..026e7f1e6 100644 --- a/docs/concepts/mcp-primitives.mdx +++ b/docs/concepts/mcp-primitives.mdx @@ -356,7 +356,7 @@ mcp-agent supports authentication for MCP servers: | Prompts | ✅ | ✅ | ✅ | ✅ | Fully Supported | | Roots | ✅ | ✅ | ✅ | ✅ | Fully Supported | | Elicitation | ✅ | ✅ | ✅ | ✅ | Fully Supported | -| Sampling | 🚧 | 🚧 | 🚧 | 🚧 | Coming Soon | +| Sampling | ✅ | ✅ | ✅ | ✅ | Coming Soon | ## Complete Examples @@ -373,4 +373,4 @@ mcp-agent supports authentication for MCP servers: Official MCP specification - \ No newline at end of file + From c292eea3e44fd1ae544d1b6b345c19c17bcead75 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 18:30:03 -0400 Subject: [PATCH 05/12] adding snippets for mcp-agent cloud and reversing tools via decorator order --- docs/cloud/agent-server.mdx | 104 +++++++++++++++++++++++------------- 1 file changed, 67 insertions(+), 37 deletions(-) diff --git a/docs/cloud/agent-server.mdx b/docs/cloud/agent-server.mdx index 008591bbf..322edb7c6 100644 --- a/docs/cloud/agent-server.mdx +++ b/docs/cloud/agent-server.mdx @@ -17,7 +17,41 @@ When you expose an agent as an MCP server, the framework: 3. Provides standard workflow management tools 4. Handles protocol communication -## Default MCP Tools +## Tools via Decorators + +### @app.tool - Synchronous Tools + +Synchronous tools execute immediately and return results: + +```python +@app.tool +def calculate_sum(a: int, b: int) -> int: + """Add two numbers together.""" + return a + b +``` + +This creates a single MCP tool `calculate_sum` that executes synchronously. + +### @app.async_tool - Asynchronous Tools + +Asynchronous tools run as durable workflows: + +```python +@app.async_tool +async def research_topic(topic: str) -> str: + """Research a topic using multiple sources.""" + # Long-running research operation + results = await gather_information(topic) + return results +``` + +This creates: +- `research_topic`: Starts the workflow +- Status tracking via `workflows-get_status` +- Cancellation via `workflows-cancel` + + +## Built-in MCP Tools Every agent server automatically provides these workflow management tools: @@ -79,39 +113,6 @@ Cancels a running workflow instance. - `run_id`: The run instance ID - `workflow_name`: Workflow identifier -## Custom Tools via Decorators - -### @app.tool - Synchronous Tools - -Synchronous tools execute immediately and return results: - -```python -@app.tool -def calculate_sum(a: int, b: int) -> int: - """Add two numbers together.""" - return a + b -``` - -This creates a single MCP tool `calculate_sum` that executes synchronously. - -### @app.async_tool - Asynchronous Tools - -Asynchronous tools run as durable workflows: - -```python -@app.async_tool -async def research_topic(topic: str) -> str: - """Research a topic using multiple sources.""" - # Long-running research operation - results = await gather_information(topic) - return results -``` - -This creates: -- `research_topic`: Starts the workflow -- Status tracking via `workflows-get_status` -- Cancellation via `workflows-cancel` - ## Server Configuration ### Basic Setup @@ -145,13 +146,25 @@ uv run mcp-agent serve --app my_agent:app uv run mcp-agent serve --app my_agent:app --transport sse ``` +#### Deploying to **mcp-agent cloud** +Update your secrets +```yaml mcp_agent.secrets.yaml +openai: + api_key: !developer_secret +``` + +```bash +uv run mcp-agent login +uv run mcp-agent deploy my_agent +``` + ## Client Configuration ### Claude Desktop -Add to `claude_desktop_config.json`: +For local mcp servers, add to `claude_desktop_config.json`: -```json +```json claude_desktop_config.json { "mcpServers": { "my-agent": { @@ -162,6 +175,23 @@ Add to `claude_desktop_config.json`: } ``` +For **mcp-agent cloud**, add to `claude_desktop_config.json`: + +```json claude_desktop_config.json +"my_agent": { + "command": "/path/to/npx", + "args": [ + "mcp-remote", + "https://[your-agent-server-id].deployments.mcp-agent-cloud.lastmileai.dev/sse", + "--header", + "Authorization: Bearer ${BEARER_TOKEN}" + ], + "env": { + "BEARER_TOKEN": "your-mcp-agent-cloud-api-token" + } +} +``` + ### Programmatic Access ```python @@ -301,4 +331,4 @@ def process_data( - [Configuration Guide](/configuration) - [Workflow Patterns](/workflows/overview) -- [Cloud Deployment](/cloud/getting-started) \ No newline at end of file +- [Cloud Deployment](/cloud/getting-started) From 424cba8e81855f99a077131dbfbabf54a1d3fddb Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 18:30:51 -0400 Subject: [PATCH 06/12] lowercase mcp-agent cloud --- docs/index.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/index.mdx b/docs/index.mdx index e3941f84c..4cfeab462 100644 --- a/docs/index.mdx +++ b/docs/index.mdx @@ -176,7 +176,7 @@ Use Temporal for durable execution, automatic retries, and workflow management. ### [As a MCP Server](cloud/agent-server) Expose your agents as MCP servers that can be used by Claude Desktop, VS Code, or other MCP clients. -### [MCP Agent Cloud](cloud/overview) +### [mcp-agent cloud](cloud/overview) Deploy agents to managed cloud infrastructure with one command. ## Examples From a5835bf75e5144c2ad4fed60fbaf46d853593b61 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 18:32:11 -0400 Subject: [PATCH 07/12] lowercase mcp-agent cloud in TOC --- docs/docs.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/docs.json b/docs/docs.json index 16d0675fc..339578576 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -68,7 +68,7 @@ ] }, { - "group": "MCP Agent Cloud", + "group": "mcp-agent cloud", "pages": [ "cloud/overview", "cloud/getting-started", @@ -168,4 +168,4 @@ } ] } -} \ No newline at end of file +} From cc321cd57d9106f7208e81ed006e7f835d2d2eb0 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 19:41:05 -0400 Subject: [PATCH 08/12] updating the introduction and overview page --- docs/cloud/overview.mdx | 199 +++++++++++++++------------------------- 1 file changed, 75 insertions(+), 124 deletions(-) diff --git a/docs/cloud/overview.mdx b/docs/cloud/overview.mdx index 925fc6c39..ce84fc681 100644 --- a/docs/cloud/overview.mdx +++ b/docs/cloud/overview.mdx @@ -1,11 +1,11 @@ --- -title: MCP Agent Cloud -description: "Deploy and manage AI agents as MCP servers" +title: mcp-agent cloud +description: "[In beta] Deploy and manage AI agents as MCP servers" --- ## Overview -MCP Agent Cloud deploys your agents as MCP servers, where agent workflows become long-running MCP tools executed in a durable workflow orchestration engine (Temporal). This architecture enables: +**mcp-agent cloud** deploys your agents as MCP servers, where agent workflows become long-running MCP tools executed in a durable workflow orchestration engine (Temporal). This architecture enables: - **Agents as MCP Servers**: Your agents are exposed as standard MCP servers that any MCP client can connect to - **Workflows as Durable Tools**: Agent workflows are exposed as MCP tools that run durably via Temporal @@ -16,147 +16,98 @@ MCP Agent Cloud deploys your agents as MCP servers, where agent workflows become - **Agent Deployment**: Deploy agents as MCP servers accessible via HTTP/WebSocket - **Temporal Integration**: Durable workflow execution with automatic retries - **Secrets Management**: Secure storage and injection of API keys -- **Multi-Region Support**: Deploy to different regions for lower latency - **Monitoring**: Real-time logs, metrics, and workflow tracking -## Deployment Process +## Preparing your mcp-agent app as a server -1. Write your agent using mcp-agent framework -2. Configure deployment settings -3. Deploy with `mcp-agent deploy` -4. Access your agent via MCP protocol +1. Double check that your entrypoint python file is named `main.py` -## Architecture +When packaging your mcp-agent app for the cloud, our CLI will be searching for `main.py`. The entire directory will be deployed, so you can reference other files and upload other assets. -### Core Concept: Agents as MCP Servers +2. Make sure you have either a `pyproject.toml` or a `requirements.txt` file in your app directory. -When you deploy an agent to MCP Agent Cloud: +3. Mark your functions that you'd like to be tool calls with the `@app.tool` decorators -1. **Your agent becomes an MCP server** - Accessible via standard MCP protocol -2. **Workflows become MCP tools** - Each workflow is exposed as a tool that MCP clients can invoke -3. **Execution is durable** - Workflows run on Temporal, surviving failures and restarts -4. **Tools are long-running** - Unlike traditional tools, agent workflows can run for hours/days/weeks - -### How It Works - -```yaml +```python main.py # Your agent definition -@app.workflow -class ResearchWorkflow: - async def run(self, topic: str): - # Long-running research task - return results +@app.tool +async def research(query) -> str: + # this is where your agent logic exists (functions and calls) + return results # Becomes an MCP tool when deployed: -# Tool: "workflows-ResearchWorkflow-run" -# Returns: workflow_id and run_id for tracking -# Status: Check via "workflows-get_status" -# Cancel: Use "workflows-cancel" +# Tool: "research" +``` + +4. Mark your secrets that you'd like to safely secure for deployment + +```yaml mcp_agent.secrets.yaml +openai: + api_key: !developer_secret ``` -### Components - -- **API Gateway**: Exposes agents as MCP servers (SSE/HTTP endpoints) -- **Agent Runtime**: Containerized execution environment for your agent code -- **Temporal Cluster**: Durable workflow orchestration engine - - Workflows survive crashes and restarts - - Automatic retries with exponential backoff - - Pause/resume capabilities for human-in-the-loop - - Complete execution history and replay debugging -- **Vault**: Secure secrets management -- **Monitoring Stack**: OpenTelemetry-based observability - -### Why Temporal for Agent Workflows? - -Agent workflows are fundamentally different from simple tool calls: -- They can run for extended periods (hours/days) -- They need to survive infrastructure failures -- They require pause/resume for human approval -- They benefit from automatic retries and error handling - -Temporal provides all these capabilities out-of-the-box, making your agents production-ready. - -## Platform Capabilities - -### Deployment -- One-command deployment via CLI -- Automatic versioning -- Blue-green deployments -- Regional deployment options -- Custom domains - -### Workflow Management -- Start, pause, resume, cancel operations -- Cron-based scheduling -- Batch operations -- Priority queues -- Rate limiting - -### Observability -- Real-time workflow monitoring -- Structured logging -- OpenTelemetry tracing -- Custom metrics -- Workflow health checks - -### Security -- HashiCorp Vault integration -- End-to-end encryption -- Role-based access control -- Audit logging - -### Integrations -- MCP client compatibility (Claude Desktop, VS Code) -- Webhook notifications -- GitHub Actions -- Custom MCP servers -- Monitoring exports (Datadog, Grafana) - -## Use Cases - -- **Customer Support**: Deploy agents for handling support tickets -- **Data Analysis**: Process and analyze business data -- **Documentation**: Generate and maintain documentation -- **Code Review**: Automate code review processes -- **Multi-Agent Systems**: Coordinate multiple specialized agents -- **RAG Applications**: Retrieval-augmented generation workflows -- **Automation**: Business process automation -- **Integration**: Connect AI to existing systems - -## Technical Specifications - -- **Protocol**: Native MCP (Model Context Protocol) -- **Orchestration**: Temporal workflow engine -- **Secrets**: HashiCorp Vault -- **Deployment**: Containerized with Kubernetes -- **Monitoring**: OpenTelemetry-based -- **Languages**: Python (primary), JavaScript/TypeScript support planned -- **Regions**: US East, US West, EU West (more coming) - -## Getting Started - -### Prerequisites - -1. mcp-agent installed (`uv tool install mcp-agent`) -2. MCP Agent Cloud account -3. API keys configured - -### Quick Start +## Deploying your mcp-agent app + +1. Login into mcp-agent cloud to get your `api key` ```bash -# Install CLI -uv tool install mcp-agent +uv run mcp-agent login` +``` + +2. Deploy your app -# Configure credentials -mcp-agent configure +```bash +uv run mcp-agent deploy my-first-agent +``` -# Deploy your agent -mcp-agent deploy --app my_agent:app +## Connect to your deployed mcp-agent server + +### Claude Desktop integration + +Configure Claude Desktop to access your agent server + +```json .claude-desktop/config.json +"my-agent-server": { + "command": "/path/to/npx", + "args": [ + "mcp-remote", + "https://[your-agent-server-id].deployments.mcp-agent-cloud.lastmileai.dev/sse", + "--header", + "Authorization: Bearer ${BEARER_TOKEN}" + ], + "env": { + "BEARER_TOKEN": "your-mcp-agent-cloud-api-token" + } +} ``` +### MCP Inspector + +Run your local MCP Inspector +```bash +npx @modelcontextprotocol/inspector +``` + +Connect with the following settings +| Setting | Value | +|---|---| +| *Transport Type* | *SSE* | +| *SSE* | *https://[your-agent-server-id].deployments.mcp-agent-cloud.lastmileai.dev/sse* | +| *Header Name* | *Authorization* | +| *Bearer Token* | *your-mcp-agent-cloud-api-token* | + + +## Example Use Cases + +Explore use cases in the [examples directory](https://github.com/lastmile-ai/mcp-agent/tree/main/examples): +- [**Github to Slack agent**](https://github.com/lastmile-ai/mcp-agent/tree/main/examples/usecases/mcp_github_to_slack_agent): Deploy an agent that will give you and your team a daily report of high-pri PRs and issues from github. +- [**Research agent**](https://github.com/lastmile-ai/mcp-agent/tree/main/examples/usecases/mcp_researcher): Deploy a research agent server to do a LLM-based research across the internet. +- [**Financial analyzer agent**](https://github.com/lastmile-ai/mcp-agent/tree/main/examples/usecases/mcp_financial_analyzer): Deploy a financial analyzer agent to research information about a specific company + + ## Next Steps - [Getting Started Guide](/cloud/getting-started) - [CLI Reference](/cloud/cli-reference) - [Agent Server Documentation](/cloud/agent-server) -- [Examples](https://github.com/lastmile-ai/mcp-agent/tree/main/examples) \ No newline at end of file +- [Examples](https://github.com/lastmile-ai/mcp-agent/tree/main/examples) From ee763fa6d70c794a1b674ce62febbd059b4e462f Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 19:41:27 -0400 Subject: [PATCH 09/12] updating the agent server with mcp-agent cloud From d01c7e20bffadf56c29e9cf21157704db80d21a3 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 19:41:54 -0400 Subject: [PATCH 10/12] Update getting-started.mdx --- docs/cloud/getting-started.mdx | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/docs/cloud/getting-started.mdx b/docs/cloud/getting-started.mdx index 1d78d4f07..22b025afd 100644 --- a/docs/cloud/getting-started.mdx +++ b/docs/cloud/getting-started.mdx @@ -1,10 +1,10 @@ --- -title: Getting Started with MCP Agent Cloud +title: Getting Started with mcp-agent cloud description: "Deploy your first agent to the cloud in under 5 minutes" --- - MCP Agent Cloud is currently in open beta. Follow the instructions below to get started. For feedback, issues and feature requests, visit https://github.com/lastmile-ai/mcp-agent/issues or join our Discord at https://lmai.link/discord/mcp-agent. + mcp-agent cloud is currently in open beta. Follow the instructions below to get started. For feedback, issues and feature requests, visit our [github issues](https://github.com/lastmile-ai/mcp-agent/issues) or join [our Discord](https://lmai.link/discord/mcp-agent). ## Prerequisites @@ -31,7 +31,7 @@ Before you begin, make sure you have: - Log in to MCP Agent Cloud: + Log in to **mcp-agent cloud**: ```bash mcp-agent login @@ -44,7 +44,7 @@ Before you begin, make sure you have: Ensure your project has the required configuration files: ```yaml mcp_agent.config.yaml - execution_engine: temporal # Cloud uses Temporal + execution_engine: temporal logger: transports: [console] level: info @@ -61,7 +61,9 @@ Before you begin, make sure you have: default_model: gpt-4o ``` - > [!IMPORTANT] Swap your api_key with !developer_secret to mark what keys will be saved as secrets within mcp-agent cloud. + + Swap your api_key with !developer_secret to mark what keys will be saved as secrets within mcp-agent cloud. + ```yaml mcp_agent.secrets.yaml openai: @@ -81,8 +83,8 @@ Before you begin, make sure you have: The deployment process will: 1. Check for existing app with this name or create a new one - 2. Process your secrets file (transforming !developer_secret tags to secure handles) - 3. Bundle and upload your code using Wrangler + 2. Process your secrets file (transforming `!developer_secret` tags to secure handles) + 3. Bundle and upload your code 4. Deploy to MCP Agent Cloud's managed infrastructure You'll see output like: @@ -224,7 +226,7 @@ Your agent is now available as an MCP server. Here's how to use it: Then add to your Claude Desktop config (`~/.claude-desktop/config.json`): - ```json + ```json .claude-desktop/config.json { "servers": { "web-summarizer": { @@ -334,8 +336,7 @@ MCP_API_KEY="your-key" mcp-agent deploy my-agent MCP Agent Cloud securely handles secrets through the `mcp_agent.secrets.yaml` file: -```yaml -# mcp_agent.secrets.yaml +```yaml mcp_agent.secrets.yaml openai: api_key: !developer_secret # Will be stored securely From bc7312644924bbaf4e69db47d587a10136599415 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 19:44:07 -0400 Subject: [PATCH 11/12] Update deploying-mcp-servers.mdx --- docs/cloud/deploying-mcp-servers.mdx | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/docs/cloud/deploying-mcp-servers.mdx b/docs/cloud/deploying-mcp-servers.mdx index 9b8ec2143..a31cafa7e 100644 --- a/docs/cloud/deploying-mcp-servers.mdx +++ b/docs/cloud/deploying-mcp-servers.mdx @@ -5,9 +5,9 @@ description: "Deploy standard MCP servers to MCP Agent Cloud infrastructure" ## Overview -MCP Agent Cloud can deploy both AI agents **and** standard MCP servers. Since agents deployed to MCP Agent Cloud are exposed as MCP servers themselves, the platform naturally supports deploying any MCP-compatible server implementation. +**mcp-agent cloud** can deploy both AI agents **and** standard MCP servers. Since agents deployed to **mcp-agent cloud** are exposed as MCP servers themselves, the platform naturally supports deploying any MCP-compatible server implementation. -This means you can use MCP Agent Cloud to: +This means you can use **mcp-agent cloud** to: - Deploy regular MCP servers built with FastMCP or other frameworks - Host tool servers that don't use AI workflows - Deploy resource servers for data access @@ -44,7 +44,7 @@ async def current_weather_resource(): """Provide current weather data.""" return {"temperature": 72, "condition": "sunny"} -# Deploy with MCP Agent Cloud +# Deploy with mcp-agent cloud # mcp-agent deploy my-weather-server ``` @@ -168,7 +168,7 @@ async def create_ticket(title: str, description: str) -> dict: The deployment process is identical whether you're deploying a simple MCP server or a full agent: ```bash -# 1. Authenticate with MCP Agent Cloud +# 1. Authenticate with mcp-agent cloud mcp-agent cloud auth login # 2. Deploy your server @@ -181,18 +181,17 @@ mcp-agent cloud servers describe mcp-agent configure --client claude ``` -## Benefits of Using MCP Agent Cloud +## Benefits of Using **mcp-agent cloud** -Even for simple MCP servers, MCP Agent Cloud provides: +Even for simple MCP servers, **mcp-agent cloud** provides: ### Infrastructure Management - Automatic SSL/TLS termination - Load balancing and auto-scaling -- Regional deployment options - High availability ### Security -- Secure secrets management via Vault +- Secure secrets management - Authentication and authorization - End-to-end encryption - Audit logging From 0903d7bc1baf6c8d5b7bf14bb216b1845f3349f6 Mon Sep 17 00:00:00 2001 From: Andrew Hoh <129882602+andrew-lastmile@users.noreply.github.com> Date: Mon, 15 Sep 2025 20:12:06 -0400 Subject: [PATCH 12/12] Update docs/cloud/overview.mdx Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com> --- docs/cloud/overview.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cloud/overview.mdx b/docs/cloud/overview.mdx index ce84fc681..1306fa527 100644 --- a/docs/cloud/overview.mdx +++ b/docs/cloud/overview.mdx @@ -51,7 +51,7 @@ openai: 1. Login into mcp-agent cloud to get your `api key` ```bash -uv run mcp-agent login` +uv run mcp-agent login ``` 2. Deploy your app