{
"markdown": "\n\n# ⚡ MaxoPerf MCP Server\n\n### Drive the entire MaxoPerf platform from any AI agent — with your API key.\n\n**A remote, hosted [Model Context Protocol](https://modelcontextprotocol.io) 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.**\n\n[](https://modelcontextprotocol.io)\n[](https://claude.ai)\n[](https://cursor.com)\n[](https://chatgpt.com)\n\n```\nhttps://app.maxoperf.com/mcp\n```\n\n
\n\n---\n\n## Configuration\n\nIt'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**):\n\n```json\n{\n \"mcpServers\": {\n \"maxoperf\": {\n \"type\": \"http\",\n \"url\": \"https://app.maxoperf.com/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer ${MAXOPERF_API_KEY}\"\n }\n }\n }\n}\n```\n\nYour 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).\n\n## Install (pick your client)\n\n**Claude Code** — the plugin bundles the server **and** the agent skill:\n```\n/plugin marketplace add MaxoPerf/mcp\n/plugin install maxoperf\n```\nOr add just the connector:\n```\nclaude mcp add --transport http maxoperf https://app.maxoperf.com/mcp \\\n --header \"Authorization: Bearer ${MAXOPERF_API_KEY}\"\n```\n\n**Cursor** · **VS Code / Copilot** · **Codex** · **ChatGPT** · **Claude Desktop** — one-click deeplinks and copy-paste config in [`packaging/`](./packaging). All use the same `mcpServers` block above.\n\n---\n\n## Tools\n\n29 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.\n\n**Context & tenancy**\n- `whoami` — Resolve the account + default workspace behind your API key\n- `list_workspaces` — List workspaces visible to the account\n- `set_active_workspace` — Set the active workspace for the session\n- `list_projects` — List projects (with edit/delete permissions)\n- `create_project` — Create a project\n\n**Tests**\n- `list_tests` — List tests (filter by project / workspace / type)\n- `get_test` — Get one test + its validation summary\n- `create_test` — Create a test shell (choose the engine/executor)\n- `get_test_overview` — Run-history overview for a test\n\n**Test files**\n- `upload_test_file` — Upload a script/data file in one call (real 3-step presigned flow)\n- `list_test_files` — List a test's files + upload state\n- `download_test_file` — Get a short-lived download URL for a file\n\n**Runs**\n- `start_run` — Launch a load/browser run on managed cloud runners (idempotent)\n- `get_run_status` — Poll lifecycle status (queued → running → passed/failed/cancelled)\n- `list_runs` — Paginated run history with filters\n- `cancel_run` — Cancel a run (destructive; hidden in read-only)\n- `rerun_run` — Re-run from a snapshot or the current test\n- `add_runners` — Scale a live run up at existing locations\n\n**Results**\n- `get_run_results` — KPI overview: throughput, latency percentiles, error rate\n- `query_run_metrics` — Time-series metrics (latency / throughput / errors / load / health)\n- `get_run_errors` — Grouped error rows (message / count / code)\n\n**Diagnostics — root-cause & anomaly detection**\n- `get_run_summary` — Executive summary + which failure criteria tripped\n- `get_run_error_bodies` — Sampled error request/response bodies + status codes\n- `get_run_logs` — Error-level engine/system log lines\n- `get_runner_health` — Runner CPU/mem trend + targetVus vs peakAchievedVus (vuShortfallPct)\n- `detect_run_anomalies` — Deterministic robust-outlier scan (median/MAD); terminal-gated, low false-positive\n\n**Escape hatch & discovery**\n- `call_platform_api` — Reach any public `/v1/*` endpoint (secrets, environments, schedules, BYOC); admin/internal deny-listed, SSRF-safe\n- `get_openapi` — The public OpenAPI document\n- `search_endpoints` — Keyword search over the API to find the right endpoint\n\n## Prompts\n\nText recipes that encode the correct tool sequence — great for chat-only clients that can't read a repo:\n\n- `run-baseline-load-test` — Start a baseline run and watch it to completion\n- `diagnose-latency-regression` — Compare p95 across two runs\n- `summarize-run` — Plain-language summary of one run\n- `plan-and-build-test` — Turn a goal into project → test → upload → run\n- `choose-executor` — Recommend an engine (k6 / JMeter / Playwright / Selenium)\n- `scan-endpoints-for-hotspots` — Rank likely hotspots from an OpenAPI spec or pasted list\n- `setup-secrets-and-envs` — Wire workspace secrets + multi-env before a run\n- `diagnose-run-failure` — Ranked root cause for a failed run\n- `explain-run-anomalies` — Explain each detected outlier\n\n## Resources\n\n- `maxoperf://openapi` — The public OpenAPI spec\n- `maxoperf://run/{id}` — A run report summary\n\n---\n\n## Try it\n\n- \"Load test https://api.example.com/checkout with 500 users for 5 minutes and fail it if p95 goes over 800ms.\"\n- \"Scan my repo for the endpoints most worth load-testing, then build and run a test for the riskiest one.\"\n- \"Why did run run-0000000001 fail? Check the errors, the logs, and whether the runners actually reached the target load.\"\n\n## Pair it with the brain\n\nThe MCP server is the **hands**. The bundled **[MaxoPerf agent skill](https://github.com/MaxoPerf/agent-skill)** (`npx @maxoperf/agent-skill install`, included in the Claude plugin, or in [`agent-skill/`](./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.\n\n## What's in this repo\n\n| Path | What |\n| --- | --- |\n| [`.claude-plugin/`](./.claude-plugin) | Claude Code plugin (bundles the MCP connector + the skill) |\n| [`agent-skill/`](./agent-skill) | A copy of the `maxoperf` agent skill (canonical home: [MaxoPerf/agent-skill](https://github.com/MaxoPerf/agent-skill)) |\n| [`packaging/`](./packaging) | MCP Registry `server.json`, `.mcpb`, VS Code / Cursor deeplinks, Codex / ChatGPT setup |\n| [`LAUNCHGUIDE.md`](./LAUNCHGUIDE.md) | MCP directory listing metadata |\n\n---\n\n\n\n**[Get started →](https://maxoperf.com)** · **[Agent skill →](https://github.com/MaxoPerf/agent-skill)** · **[Docs →](https://maxoperf.com/docs)**\n\nRead-only mirror of the MaxoPerf monorepo. File issues at [maxoperf.com](https://maxoperf.com).\n\n
\n",
"bytes": 7012,
"sha": "c6c3f424855ff79918ee58c91fdc4d654e4d0ab032db47bf06fb49c7c026ca77",
"repo_slug": "maxoperf/mcp",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_com_maxoperf_maxoperf_396dd783/readme"
}