OpenMark のリモート MCP サーバーとは何ですか?
OpenMark のリモート MCP サーバーは、https://openmark.ai/mcp にホストされた Model Context Protocol エンドポイントです。AI アシスタントはローカルに何もインストール・実行することなく接続できます。
OpenMark MCP Server認証済み注目
@OpenMark AI
基本情報
OpenMark MCP Server について
OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
接続情報
https://openmark.ai/mcpセットアップ
claude mcp add openmark --transport http https://openmark.ai/mcp --header "Authorization: Bearer om_YOUR_KEY"OpenMark MCP Server のツール
9How to write an OpenMark task: the YAML structure, all 18 scoring modes, and tips. Call this before writing a task. Pass a topic for the full detail on one subject (the app's Task Guide): fields, scoring, composite, chaining, documents, examples, best_practices, or a scoring mode name.
Check a task YAML the way OpenMark will before running it: structure, scoring settings, and the test limit of the user's plan. Free, saves nothing. Returns the problems to fix and warnings worth a look.
Current OpenMark model ids with list prices ($ per 1M tokens), as text and as a structured list. Use these ids in run_benchmark. Append @low, @medium or @high to a reasoning model id to set its reasoning effort.
Get an upload_uid and a one-hour upload link (no API key needed) for images, PDFs or text documents, with the exact curl command. Upload the files, reference them by file name in each test's attachments list, then pass the upload_uid to estimate_cost / run_benchmark.
Credits a run_benchmark call would use, before spending anything: the expected total, the split per model, the balance needed to start, the worst case, and the user's balance. Same inputs and run settings as run_benchmark. Use it to drop an expensive model, or to compare settings (e.g. max_tokens), before running.
Save a task (YAML, see get_task_format) to the user's OpenMark account and run it on the given models with real API calls. Returns a job_id and the expected cost; poll get_results. Spends the user's credits; pass max_credits to only start within a budget. Optional run settings match the app's Configure & Run panel (preset, stability_runs, max_tokens, temperature_discovery, temp_preference, timeout_profile, custom_timeout, fail_fast).
Status of a benchmark job, and once completed the ranked results (score, stability, cost per run, latency), the tests each model missed with its answer, a recommendation for the chosen objective and quick picks for the others.
The user's plan, credit balance and limits, and what a credit pack, Pro or Expert would unlock. Use it before large runs, or when a run is refused for credits or limits.
Watch the task of a completed job: when new or cheaper models ship, OpenMark re-tests up to 4 of them next to the user's pick and emails the user only when one beats it. Each check uses the user's credits at the normal rate.
概要
What is OpenMark
OpenMark benchmarks the prompt in your code on 100+ models with real API calls and deterministic scoring, then choose the winner by accuracy, cost, speed, or any mix of those.
Website: http://www.openmark.ai
Tools
- get_task_format: write a fair test from your real prompt
- list_models: current model ids and prices
- run_benchmark: run the test on the models you pick
- get_results: score, stability, cost, and latency
- watch_task: get an email when a new model beats the winner
Connect
Create a key at https://openmark.ai/ui (account menu, API keys). New accounts start with 50 credits. Setup guide: https://openmark.ai/mcp
Cursor (~/.cursor/mcp.json):
{ "mcpServers": { "openmark": { "url": "https://openmark.ai/mcp", "headers": { "Authorization": "Bearer om_YOUR_KEY" } } } }
Claude Code:
claude mcp add --transport http openmark https://openmark.ai/mcp --header "Authorization: Bearer om_YOUR_KEY"
It is getting constantly updated, so check the project page for more up to date information !
よくある質問
OpenMark の MCP サーバーにはどう接続しますか?
エンドポイント https://openmark.ai/mcp を Claude Code、Cursor、VS Code など任意の MCP 対応クライアントに追加してください。このページのセットアップ手順で各クライアントを一度に設定できます。
OpenMark の MCP サーバーは認証が必要ですか?
はい。OpenMark は API キーが必要です——取得方法は公式ドキュメントを確認し、クライアントの設定に追加してください。
OpenMark の MCP サーバーはどのトランスポートを使用しますか?
OpenMark は Streamable HTTP エンドポイントを公開しており、これはリモート MCP サーバーで広く使われ、主要な MCP クライアントがサポートするトランスポートです。
他のリモート MCP サーバー
AIsa
AIsa is one key for 950+ data APIs across SEO and AI visibility, finance, social, web search, sales and agent mail — the go-to-market data stack behind prospecting, competitor research and brand monitoring. Five tools ra
AdaptlyPost
AdaptlyPost: Schedule and publish social posts to Instagram, TikTok, YouTube, X, Facebook, LinkedIn, Pinterest, Threads, and Bluesky from any MCP client.
%20-%20Sarah%20Xu.svg){kind=icon}
Adobe Journey Optimizer
Understand and troubleshoot your Journeys and Campaigns
A
AccountHub
One MCP connection for all your Gmail, Google Calendar, Drive and Contacts accounts, Slack workspaces and Notion — free.
Adobe Experience Manager
Manage your Adobe Experience Manager content
コメント