Octoperf MCP Server

Drive OctoPerf load testing from any AI agent: import, edit, validate, run scenarios, read metrics.

Remote serverstreamable-http

What is the Octoperf MCP server?

Most browser automation work still happens through a UI a human drives. Octoperf MCP server moves it into the conversation instead. Drive OctoPerf load testing from any AI agent: import, edit, validate, run scenarios, read metrics.

The short version

The first MCP call opens a browser for OAuth login on api.octoperf.com. Revoke at any time from Account → Connected applications on OctoPerf.

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

The tools it exposes

The server publishes 12 tools. What each one is for:

  • Component — Location
  • AGENTS.md — plugins/octoperf/AGENTS.md
  • Skills — plugins/octoperf/skills/*/SKILL.md
  • Skill — Triggers on
  • octoperf-auto-correlation — "correlate the VU", "fix replay errors", "401/403 on replay"
  • octoperf-validation-triage — "the validation is red", "lots of errors after import"
  • octoperf-scenario-diagnosis — "the load test failed", "why are response times so high"
  • octoperf-bench-reports — "what's the right tool for this widget", widget metric questions
  • octoperf-export-bench-report-pdf — "export the report as PDF", "print the bench report", "share a PDF"
  • octoperf-real-browser-probe — "EUM probe", "Playwright probe", "TruClient equivalent"
  • octoperf-scheduling — "schedule the scenario", "run every weekday at 8am"
  • octoperf-async-polling — invoked automatically by any skill that has to poll a taskId result

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Octoperf.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Octoperf's toolset — Component, AGENTS.md, Skills and 9 more — is a fair guide to whether it matches your workflow. It is maintained by OctoPerf; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Octoperf's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
ComponentLocation
AGENTS.mdplugins/octoperf/AGENTS.md
Skillsplugins/octoperf/skills/*/SKILL.md
SkillTriggers on
octoperf-auto-correlation"correlate the VU", "fix replay errors", "401/403 on replay"
octoperf-validation-triage"the validation is red", "lots of errors after import"
octoperf-scenario-diagnosis"the load test failed", "why are response times so high"
octoperf-bench-reports"what's the right tool for this widget", widget metric questions
octoperf-export-bench-report-pdf"export the report as PDF", "print the bench report", "share a PDF"
octoperf-real-browser-probe"EUM probe", "Playwright probe", "TruClient equivalent"
octoperf-scheduling"schedule the scenario", "run every weekday at 8am"
octoperf-async-pollinginvoked automatically by any skill that has to poll a taskId result

Example prompts to try

  • Use Octoperf to Component.
  • Use Octoperf to AGENTS.md.
  • Use Octoperf to Skills.

Frequently asked questions

It connects Octoperf to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (Component, AGENTS.md, Skills, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Octoperf directly.