> For the complete documentation index, see [llms.txt](https://docs.opsmx.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.opsmx.com/ai-assistant-and-experience-studio/experience-interafaces-and-plugins/mcp-server.md).

# MCP Server

The MCP (Model Context Protocol) Server acts as the foundational communication layer for the OpsMx AI Assistant ecosystem. It enables structured and standardized interactions between AI models, enterprise systems, operational tools, and user interfaces.

The MCP Server manages how context is shared, actions are triggered, and workflows are coordinated across distributed environments. It ensures that the AI Assistant always operates with accurate and relevant contextual information such as deployment states, pipeline metadata, infrastructure events, user intent, security posture, and operational history.

By centralizing context management and communication protocols, the MCP Server creates a reliable and scalable framework for integrating AI-driven intelligence into DevOps, security, and operational workflows.

## Why we use it in OpsMx

OpsMx uses the MCP Server to provide secure, context-aware, and scalable communication between AI systems and enterprise platforms. The objective is to ensure that AI-assisted operations are reliable, governed, and capable of operating consistently across complex software delivery environments.

## How we use it in OpsMx

OpsMx uses the MCP Server as the orchestration and context management backbone for AI-assisted DevOps, security, and operational workflows.

### Context-aware AI interactions

The MCP Server continuously manages and distributes contextual information including:

* Deployment states
* Pipeline execution data
* Infrastructure telemetry
* Security events
* User interactions
* Operational history

This allows the AI Assistant to provide accurate, relevant, and actionable responses across environments.

### Tool and plugin orchestration

OpsMx uses the MCP Server to coordinate communication between:

* CI/CD platforms
* Security systems
* Observability tools
* Collaboration platforms
* IDE integrations
* Governance engines

This enables plugins and integrations to operate consistently across distributed workflows.

### Secure action execution

The MCP Server validates permissions, policies, and operational context before allowing AI-triggered actions such as:

* Deployment approvals
* Rollbacks
* Pipeline execution
* Incident remediation
* Security enforcement

This ensures that automation operates within enterprise governance controls.

### Multi-interface intelligence delivery

The MCP Server enables consistent AI interactions across multiple interfaces including:

* Chat platforms
* Developer environments
* Pull request systems
* Dashboards
* Conversational AI interfaces

This creates a unified AI experience regardless of where users interact with the system.

## Core capabilities of the MCP Server

| Capability                 | Description                                               |
| -------------------------- | --------------------------------------------------------- |
| Context management         | Centralized operational and workflow context handling     |
| Protocol standardization   | Structured communication between systems and AI models    |
| Workflow orchestration     | Coordination of AI-driven actions and integrations        |
| Secure interaction control | Governance, access control, and policy enforcement        |
| Multi-platform integration | Support for distributed tools and interfaces              |
| Scalable architecture      | Modular and extensible enterprise communication framework |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.opsmx.com/ai-assistant-and-experience-studio/experience-interafaces-and-plugins/mcp-server.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.