Skip to content

Innovation

Designing a Token-Efficient MCP Server: the OctoPerf Approach

In the first two articles of this series we showed what the OctoPerf MCP Server does. This one is for the builders: how we designed it, and specifically how we kept its token cost under control.

Because here is the thing nobody tells you when you start writing a Model Context Protocol server: the hard part is not exposing your API to an LLM. The hard part is not exposing too much of it. Every byte a tool returns lands in the model's context window, where it costs money, adds latency, and dilutes the model's attention. A server that naively mirrors a REST API produces an agent that is expensive, slow, and confused.

This article walks through the five patterns we applied to avoid that fate. None of them is specific to load testing: if you are building an MCP server for your own product, they should transfer directly.

OctoPerf MCP Server in Action: Browser Probes, Scheduled Runs and Smarter Reports

In our previous article we introduced the OctoPerf MCP Server and followed three skills (validation triage, auto-correlation, scenario diagnosis) through a complete workflow: from a raw HAR recording to a diagnosed 500-user load test.

This second part covers the remaining skills, and they take the story further: measuring what real users perceive during the load with a Playwright browser probe, turning the test into a recurring schedule, and letting the agent read the resulting reports widget by widget, trends included. Same format as before: the actual conversation between a user and the LLM, then the matching result in OctoPerf.

Introducing the OctoPerf MCP Server: Load Testing from Your AI Assistant

We are excited to announce the official release of the OctoPerf MCP Server. Built on the open Model Context Protocol, it lets any AI agent (Claude.ai, Claude Code, Codex, Gemini CLI, GitHub Copilot and more) drive your OctoPerf account directly: import Virtual Users, fix replay errors, run scenarios and read back metrics, all in plain language, without leaving the chat.

In this article we first present the server globally: what it exposes, how authentication works, and how to connect your favorite client in minutes. We then follow a complete, realistic workflow through three of the bundled skills: validation triage, auto-correlation and scenario diagnosis, showing the actual conversation between a user and the LLM, and the matching result in OctoPerf.

Why Modern Teams Need a Bridge Between Open Source and Enterprise Performance Testing

Modern performance testing is evolving beyond the traditional choice between enterprise platforms and open-source tools. Teams increasingly need the flexibility of JMeter, k6, Gatling, or Locust combined with enterprise-grade reporting, scalability, security, and support.

A new generation of platforms helps reduce operational complexity, lower total cost of ownership, and accelerate adoption through AI-assisted workflows and simplified onboarding. OctoPerf exemplifies this approach by combining open-source compatibility with enterprise capabilities, flexible deployment options, predictable pricing, and strong security practices.

The goal is no longer to choose between open source and enterprise software, but to leverage the strengths of both.

Trend Reports: Stop Comparing Load Test Results in Spreadsheets

This post is the second in our "Features Sitting Idle" series, where we explore key OctoPerf features that are either misused, misunderstood, or simply unknown to most users.

Features Sitting Idle - Trend Reports

"Sprint Done. Has Your Performance Regressed Since the Last Release?"

The question comes up every iteration, and yet teams usually handle it the same way: export two reports, open a spreadsheet, and compare numbers manually.

It works, but it doesn't scale. After three or four sprints, no one wants to open another spreadsheet.