OpenMark MCP server
ai.openmark/openmarkopenmark.aistreamable-httpv1.0.0Scanned
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
10 tools: 4 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the OpenMark MCP server can do
The OpenMark MCP server is published by openmark.ai, a domain the MCP Registry verified. It has 10 tools. It can create or change data (4 tools: estimate_cost, run_benchmark, export_openclaw_csv and watch_task), but cannot delete data. 6 tools only read.
1 tool reads private data (prepare_attachments).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 4Claude Code: ask
estimate_costCredits 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
export_openclaw_csvA completed job's results as the CSV the OpenMark Router plugin for OpenClaw reads (the same file as the app's Export > OpenClaw).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it A completed job's results as the CSV the OpenMark Router plugin for OpenClaw reads (the same file as the app's Export > OpenClaw). Save it in the plugin's benchmarks folder, by default ~/.openclaw/workspace/plugins/openmark-router/benchmarks/, and OpenClaw routes this kind of task to the benchmark winner. Free.
run_benchmarkSave a task (YAML, see get_task_format) to the user's OpenMark account and run it on the given models with real API calls.No findings
Why it is in this group
- The name "run_benchmark" says "run": a word for a change.
Description, as the server wrote it 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).
watch_taskWatch 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Only reads 6Show 6 read-only tools
get_accountThe user's plan, credit balance and limits, and what a credit pack, Pro or Expert would unlock.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it 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.
get_resultsStatus 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 ch…No findings
Why it is in this group
- The name "get_results" says "get": a word for reading.
Description, as the server wrote it 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.
get_task_formatHow to write an OpenMark task: the YAML structure, all 18 scoring modes, and tips.No findings
Why it is in this group
- The name "get_task_format" says "get": a word for reading.
Description, as the server wrote it How 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.
list_modelsCurrent OpenMark model ids with list prices ($ per 1M tokens), as text and as a structured list.No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it 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.
prepare_attachmentsGet an upload_uid and a one-hour upload link (no API key needed) for images, PDFs or text documents, with the exact curl command.Reads private dataNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "document": it reads documents.
- private-dataThe input names a file (input.file_names), and the tool reads: it reads files.
Description, as the server wrote it 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.
validate_taskCheck a task YAML the way OpenMark will before running it: structure, scoring settings, and the test limit of the user's plan.No findings
Why it is in this group
- The name "validate_task" says "validate": a word for reading.
Description, as the server wrote it 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.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:27 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://openmark.ai/mcp: tools/list returned 10 tools to an anonymous client, including estimate_cost (write), run_benchmark (write), export_openclaw_csv (write), watch_task (write)
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 3 to 4
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:export_openclaw_csvChanges things
- Changed:estimate_costChanges thingsinputSchema
- Changed:run_benchmarkChanges thingsinputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http openmark https://openmark.ai/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http openmark https://openmark.ai/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__openmark__get_task_format",
"mcp__openmark__validate_task",
"mcp__openmark__list_models",
"mcp__openmark__prepare_attachments",
"mcp__openmark__get_results",
"mcp__openmark__get_account"
],
"ask": [
"mcp__openmark__estimate_cost",
"mcp__openmark__run_benchmark",
"mcp__openmark__export_openclaw_csv",
"mcp__openmark__watch_task"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as openmark. Review it before you use it.
Capability tags behind 1 rule
- mcp__openmark__prepare_attachments private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.openmark/openmark/verify?hash=5e3b11fb22b3c3ea0b437a55150d2fb875f10d419f87df93e61fd579334e5ae5" | jq -e '.changed == false'Pinned hash 5e3b11fb22b3, from Nov 11, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.openmark/openmark/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.openmark/openmark)Source: MCP Registry. Synced Oct 21, 2026, 17:42 UTC.
OpenMark MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OpenMark MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the OpenMark MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OpenMark MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the OpenMark MCP server have?
- 10 tools: 4 write, 6 read. estimate_cost, run_benchmark, export_openclaw_csv, watch_task, get_task_format, validate_task, list_models, prepare_attachments and 2 more.
Does the OpenMark MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OpenMark MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the OpenMark MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.