# Connect your AI to Zato documentation via MCP

Your copilot reads the current Zato documentation over MCP and answers your questions from it.

Your AI can read the Zato documentation over MCP, so its answers about development with Zato, its configuration and its architecture come from the current pages instead of training data.

With each question, the copilot searches the documentation in real time and retrieves the exact content it needs before answering.

## Set up {#set-up}

Point your AI to this address:

[https://zato.io/mcp](https://zato.io/mcp)

> **Claude Code**
>
> Run this command to add the Zato documentation as an MCP server:
>
> ```bash
> claude mcp add --transport http zato-docs https://zato.io/mcp
> ```
>
> Start Claude Code and ask a question - it searches the documentation and reads the pages it needs:
>
> claude\~/projects/my-app
>
> How do I schedule a service to run every hour?
>
> zato-docs - search\_documentation (MCP)(query: "schedule a service to run every hour")
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> zato-docs - get\_document\_content (MCP)(document\_path: "tutorials/python-scheduler.html")
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **Claude Web**
>
> - Go to your account settings and click **Add custom connector**
>
> - Set name to **Zato Docs**
> - Set URL to **https://zato.io/mcp**
>
> - Click **Configure**
>
> - Let Claude always use all the Zato Docs tools
>
> - Claude now has live access to the Zato documentation

> **GitHub Copilot**
>
> Create `.vscode/mcp.json` in your project (or add the server to your user settings):
>
> ```json
> {
>   "servers": {
>     "zato-docs": {
>       "type": "http",
>       "url": "https://zato.io/mcp"
>     }
>   }
> }
> ```
>
> Open the Chat view in agent mode and ask a question:
>
> CHATAgent · GPT-5
>
> user
>
> How do I schedule a service to run every hour?
>
> GitHub Copilot
>
> Ran zato-docs/search\_documentation {"query": "schedule a service to run every hour"}
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> Ran zato-docs/get\_document\_content {"document\_path": "tutorials/python-scheduler.html"}
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **Codex**
>
> Run this command to add the Zato documentation as an MCP server:
>
> ```bash
> codex mcp add zato-docs --url https://zato.io/mcp
> ```
>
> Start Codex and ask a question:
>
> codex\~/projects/my-app
>
> How do I schedule a service to run every hour?
>
> Called zato-docs.search\_documentation({"query": "schedule a service to run every hour"})
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> Called zato-docs.get\_document\_content({"document\_path": "tutorials/python-scheduler.html"})
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **Cursor**
>
> Create `.cursor/mcp.json` in your project (or `~/.cursor/mcp.json` for all projects):
>
> ```json
> {
>   "mcpServers": {
>     "zato-docs": {
>       "url": "https://zato.io/mcp"
>     }
>   }
> }
> ```
>
> Open the agent panel and ask a question:
>
> Agentmy-app
>
> How do I schedule a service to run every hour?
>
> Called MCP tool search\_documentation zato-docs
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> Called MCP tool get\_document\_content zato-docs
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **Gemini CLI**
>
> Run this command to add the Zato documentation as an MCP server:
>
> ```bash
> gemini mcp add --transport http zato-docs https://zato.io/mcp
> ```
>
> Start Gemini CLI and ask a question:
>
> gemini\~/projects/my-app
>
> How do I schedule a service to run every hour?
>
> search\_documentation (zato-docs MCP Server) {"query": "schedule a service to run every hour"}
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> get\_document\_content (zato-docs MCP Server) {"document\_path": "tutorials/python-scheduler.html"}
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **OpenCode**
>
> Add the server to `opencode.json` in your project (or `~/.config/opencode/opencode.json` for all projects):
>
> ```json
> {
>   "$schema": "https://opencode.ai/config.json",
>   "mcp": {
>     "zato-docs": {
>       "type": "remote",
>       "url": "https://zato.io/mcp",
>       "enabled": true
>     }
>   }
> }
> ```
>
> Start OpenCode and ask a question:
>
> opencodeclaude-sonnet-4
>
> How do I schedule a service to run every hour?
>
> zato-docs\_search\_documentation {"query": "schedule a service to run every hour"}
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> zato-docs\_get\_document\_content {"document\_path": "tutorials/python-scheduler.html"}
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

> **Antigravity**
>
> Add the server to `~/.gemini/config/mcp_config.json` (or `.agents/mcp_config.json` in your project) - Antigravity uses `serverUrl`, not `url`:
>
> ```json
> {
>   "mcpServers": {
>     "zato-docs": {
>       "serverUrl": "https://zato.io/mcp"
>     }
>   }
> }
> ```
>
> Open the agent panel and ask a question:
>
> AgentGemini 3 Pro
>
> How do I schedule a service to run every hour?
>
> MCP: zato-docs · search\_documentation
>
> {"query": "schedule a service to run every hour", "count": 3, "results": \[{"title": "Python Scheduler", "path": "tutorials/python-scheduler.html", "score": 12.3148}, {"title": "Run services on a schedule", "path": "docs/dev/examples/scheduler.html", "score": 9.8721}, {"title": "File transfer schedules", "path": "docs/dev/file-transfer/schedules.html", "score": 6.0215}\]}
>
> MCP: zato-docs · get\_document\_content
>
> Python Scheduler - Learn how to schedule Python code, API calls and SQL jobs with Zato. Select "Scheduler" in the main menu, click "Create a new job: interval-based" … (14,208 characters)
>
> Use an interval-based scheduler job. In the Dashboard open **Scheduler**, click **Create a new job: interval-based**, choose the service to run, set **Hours** to 1 and click OK - the scheduler now invokes that service every hour. The job can also be kept as enmasse YAML in git. The full walkthrough is in the [Python Scheduler tutorial](https://zato.io/tutorials/python-scheduler.html).

## Ask a question {#ask-a-question}

Try other questions, for instance:

- *"How do I install Zato on Windows? And Mac?"*
- *"What's the difference between a channel and an outgoing connection?"*
- *"How to query MS SQL Server?"*
- *"How do I schedule a service to run every hour?"*
- *"What security options are available for REST channels?"*

The copilot searches the documentation, finds the relevant pages and answers based on what Zato supports.

## See also {#see-also}

- [MCP gateways](https://zato.io/docs/ai/mcp/index.html) - Expose your own Python services as tools for AI agents
- [Sharing with clients](https://zato.io/docs/ai/mcp/sharing-with-clients.html) - Give client teams your own gateway's details as one document
- [MCP tutorial](https://zato.io/tutorials/mcp/01.html) - A gateway built and called from Claude Code, end to end

## Learn more {#learn-more}

- [MCP tutorial](https://zato.io/tutorials/mcp/01.html) - Expose Python services as AI tools and connect Claude Code in minutes
- [AI Integrations overview](https://zato.io/docs/ai/) - Both directions of AI traffic in one platform, and where to start
- [MCP gateway reference](https://zato.io/docs/ai/mcp/) - Configuration, endpoint behavior and the governance controls
- [Tool schemas](https://zato.io/docs/ai/mcp/tool-schemas.html) - How a service's docstring and declared I/O become its tool definition
- [MCP gateway security](https://zato.io/docs/ai/mcp/security.html) - API keys, Basic Auth and bearer tokens for AI agents
- [MCP response controls](https://zato.io/docs/ai/mcp/response-controls.html) - PII removal, prompt-injection safeguards and token-denominated size caps
- [MCP audit log](https://zato.io/docs/ai/mcp/audit-log.html) - What each agent did, when and with what outcome - payloads never recorded
- [MCP alerts](https://zato.io/docs/ai/mcp/alerts.html) - Failing backends, agents stuck in a loop and gateways with too many tools
- [Cost and limits](https://zato.io/docs/ai/cost-and-limits.html) - Every setting that caps AI cost and traffic, with worked examples
- [GitOps for AI integrations](https://zato.io/docs/ai/enmasse.html) - LLM connections and MCP gateways as YAML in version control
- [AI examples](https://zato.io/docs/ai/examples/) - Complete, runnable scenarios - one real-world need per file