Power your agent
The publisher's own URL. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
https://app.maxoperf.com/mcpThe Claude button above opens Claude with the name and URL filled in. You still confirm it there.
claude mcp add --transport http com.maxoperf-maxoperf https://app.maxoperf.com/mcpRun in a terminal.
{ "mcpServers": { "com.maxoperf-maxoperf": { "command": "npx", "args": [ "-y", "mcp-remote", "https://app.maxoperf.com/mcp" ] } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
A remote, hosted Model Context Protocol server that turns Claude, Cursor, Codex, VS Code Copilot, and ChatGPT into a full performance-testing operator. Create tests, launch load runs on managed cloud runners, read results, and get root-cause analysis — all in natural language, all authenticated with your own key.
Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.
https://app.maxoperf.com/mcp
It's a remote, hosted server — nothing to install or run. Add this to your MCP client config and set MAXOPERF_API_KEY (create one in the console → Settings → API keys):
{
"mcpServers": {
"maxoperf": {
"type": "http",
"url": "https://app.maxoperf.com/mcp",
"headers": {
"Authorization": "Bearer ${MAXOPERF_API_KEY}"
}
}
}
}
Your key is validated on every call by the real platform (auth, tenancy, OpenFGA, audit) — the server stores nothing and adds no new trust boundary. Revoke the key, access dies instantly. Send the header X-MaxoPerf-MCP-Mode: read-only for a look-but-don't-touch session (write tools hidden).
Claude Code — the plugin bundles the server and the agent skill:
/plugin marketplace add MaxoPerf/mcp
/plugin install maxoperf
Or add just the connector:
claude mcp add --transport http maxoperf https://app.maxoperf.com/mcp \
--header "Authorization: Bearer ${MAXOPERF_API_KEY}"
Cursor · VS Code / Copilot · Codex · ChatGPT · Claude Desktop — one-click deeplinks and copy-paste config in packaging/. All use the same mcpServers block above.
29 curated tools. Reads default to response_format: "concise" (pass "detailed" for the full payload); write tools require a non-read-only session, and cancel_run is hidden in read-only mode.
Context & tenancy
whoami — Resolve the account + default workspace behind your API keylist_workspaces — List workspaces visible to the accountset_active_workspace — Set the active workspace for the sessionlist_projects — List projects (with edit/delete permissions)create_project — Create a projectTests
list_tests — List tests (filter by project / workspace / type)get_test — Get one test + its validation summarycreate_test — Create a test shell (choose the engine/executor)get_test_overview — Run-history overview for a testTest files
upload_test_file — Upload a script/data file in one call (real 3-step presigned flow)list_test_files — List a test's files + upload statedownload_test_file — Get a short-lived download URL for a fileRuns
start_run — Launch a load/browser run on managed cloud runners (idempotent)get_run_status — Poll lifecycle status (queued → running → passed/failed/cancelled)list_runs — Paginated run history with filterscancel_run — Cancel a run (destructive; hidden in read-only)rerun_run — Re-run from a snapshot or the current testadd_runners — Scale a live run up at existing locationsResults
get_run_results — KPI overview: throughput, latency percentiles, error ratequery_run_metrics — Time-series metrics (latency / throughput / errors / load / health)get_run_errors — Grouped error rows (message / count / code)Diagnostics — root-cause & anomaly detection
get_run_summary — Executive summary + which failure criteria trippedget_run_error_bodies — Sampled error request/response bodies + status codesget_run_logs — Error-level engine/system log linesget_runner_health — Runner CPU/mem trend + targetVus vs peakAchievedVus (vuShortfallPct)detect_run_anomalies — Deterministic robust-outlier scan (median/MAD); terminal-gated, low false-positiveEscape hatch & discovery
call_platform_api — Reach any public /v1/* endpoint (secrets, environments, schedules, BYOC); admin/internal deny-listed, SSRF-safeget_openapi — The public OpenAPI documentsearch_endpoints — Keyword search over the API to find the right endpointText recipes that encode the correct tool sequence — great for chat-only clients that can't read a repo:
run-baseline-load-test — Start a baseline run and watch it to completiondiagnose-latency-regression — Compare p95 across two runssummarize-run — Plain-language summary of one runplan-and-build-test — Turn a goal into project → test → upload → runchoose-executor — Recommend an engine (k6 / JMeter / Playwright / Selenium)scan-endpoints-for-hotspots — Rank likely hotspots from an OpenAPI spec or pasted listsetup-secrets-and-envs — Wire workspace secrets + multi-env before a rundiagnose-run-failure — Ranked root cause for a failed runexplain-run-anomalies — Explain each detected outliermaxoperf://openapi — The public OpenAPI specmaxoperf://run/{id} — A run report summaryThe MCP server is the hands. The bundled MaxoPerf agent skill (npx @maxoperf/agent-skill install, included in the Claude plugin, or in agent-skill/ here) is the brain — it reads your code, finds the hotspots, builds and runs the test, and diagnoses why it broke, driving these tools automatically.
Read-only mirror of the MaxoPerf monorepo. File issues at maxoperf.com.
© 2026 MCP Directory.
Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.
{ "mcpServers": { "com.maxoperf-maxoperf": { "url": "https://app.maxoperf.com/mcp", "headers": {} } }}Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Maxoperf is reached over HTTP.
Last checked 2026-11-08. Load & browser performance testing — drive MaxoPerf from your AI agent with your API key.