What is the OpenMark remote MCP server?
The OpenMark remote MCP server is a hosted Model Context Protocol endpoint at https://openmark.ai/mcp, so AI assistants can connect to it without installing or running anything locally.
OpenMark MCP ServerVerifiedFeatured
@OpenMark AI
Basic information
Transport
Streamable HTTP
Authentication
API Key
Category
Developer Tools
Author
OpenMark AI
Submitted by
Marc Kean Paker
About OpenMark MCP Server
OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
Connection details
https://openmark.ai/mcpSetup
claude mcp add openmark --transport http https://openmark.ai/mcp --header "Authorization: Bearer om_YOUR_KEY"OpenMark MCP Server tools
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.
Overview
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 !
Frequently asked questions
How do I connect to the OpenMark MCP server?
Add the endpoint https://openmark.ai/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Does the OpenMark MCP server require authentication?
Yes. OpenMark requires an API key — check the official documentation for how to obtain one, then include it in your client's configuration.
Which transport does the OpenMark MCP server use?
OpenMark exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
More remote MCP servers
2pr.io
Write, schedule and publish LinkedIn posts in your own voice, reply to comments and read your analytics, all from your AI assistant. Remote MCP server with OAuth sign-in.
AWS Knowledge MCP Server
Search and read current AWS documentation, check regional availability and load AWS agent skills, with no AWS account needed.
AQL PropertyCheck — Physical check of one exact address
Check one exact Gold Coast or Brisbane City property address. Free address/coverage check and short summary; paid structured Agent JSON adds available building, street and surrounding context, with Brisbane routed journe
%20-%20Sarah%20Xu.svg){kind=icon}
Adobe Experience Manager
Manage your Adobe Experience Manager content
A
ASO Atlas
App Store keyword research, rank tracking, competitor analysis and authorized performance data.
Comments