> For the complete documentation index, see [llms.txt](https://docs.qpoint.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qpoint.io/release-notes/pulse-mcp.md).

# Pulse MCP Server

**Bring Pulse traffic intelligence directly into your AI workflows.**

We're introducing the **Pulse MCP server**, a Model Context Protocol interface for querying observed network traffic, requests, issues, PII signals, and aggregate metrics from Pulse-backed data.

**Released:** Feb 20, 2025

{% hint style="success" %}
**Available Now**: Pulse MCP server support is available for AI-assisted troubleshooting and analysis workflows.
{% endhint %}

***

## What's New

### MCP Access to Core Pulse Resources

AI assistants can query structured data across:

* **Connections**
* **Requests**
* **Traffic** (aggregates, availability, bandwidth, performance)
* **Issues** (policy and API errors)
* **PII** detections

### Rich Tooling for Fast Investigation

The server exposes count/list/get/histogram/frequency patterns plus specialized tools for:

* Request duration and tag analytics
* Traffic summaries, time-series, location and geo breakdowns
* Issue/error exploration
* PII summaries and distributions

### Filter-Driven Analysis

Use field-based and fuzzy filters (`endpointId`, `vendorId`, `path`, status, direction, etc.) to narrow investigations quickly.

### Time-Aware Querying

Built-in support for RFC3339 timestamps and configurable granularity (`minute` to `year`) makes trend analysis straightforward.

***

## Why It Matters

Pulse MCP turns raw traffic intelligence into conversational, automatable workflows for engineering, security, and operations teams:

* Ask natural-language questions about live or recent traffic
* Investigate incidents with reproducible query patterns
* Build AI assistants that reason over real production telemetry
* Reduce manual dashboard hopping during outages

***

## Example Outcomes

* "Which endpoints had the highest p99 latency in the last hour?"
* "Show issue frequency by error for this vendor in prod"
* "Count requests with auth failures and list affected paths"
* "Summarize detected PII types by endpoint"

***

## Feedback

Have ideas for new MCP tools or filters?

* **GitHub Issues**: [qpoint-io/qtap](https://github.com/qpoint-io/qtap/issues)


---

# 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.qpoint.io/release-notes/pulse-mcp.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.