Search, save and rate AI tools people shared in chats. Local catalogue, any model or none.
Nothing to run from here
OpenMark is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
9
tools declared
remote
at its publisher
—
calls last 7d
What it does
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http openmark-mcp https://openmark.ai/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# get_task_format, validate_task, list_models and 6 more
It needs AUTHORIZATION (Bearer followed by your personal key (om_...) from openmark.ai/ui, account menu > API keys): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
OpenMark costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OPAll 1 server
openmark1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer followed by your personal key (om_...) from openmark.ai/ui, account menu > API keys) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http openmark-mcp https://openmark.ai/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer followed by your personal key (om_...) from openmark.ai/ui, account menu > API keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
How to write an OpenMark task: the YAML structure, all 18 scoring modes, and tips. Call this before writing a task. Pass a topic for the full detail on one subject (the app's Task Guide): fields, scoring, composite, chaining, documents, examples, best_practices, or a scoring mode name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Optional: fields, scoring, composite, chaining, documents, examples, best_practices, or a scoring mode name such as regex_match |
Check a task YAML the way OpenMark will before running it: structure, scoring settings, and the test limit of the user's plan. Free, saves nothing. Returns the problems to fix and warnings worth a look.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_yaml | string | yes | The full task YAML (a JSON object with the same fields also works) |
Current OpenMark model ids with list prices ($ 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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | Filter by id, name or provider, e.g. 'claude', 'gemini flash' |
| max_output_price | number | no | Only models at or below this $ per 1M output tokens |
| images_only | boolean | no | Only models that accept image attachments |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_names | array | no | Optional: the local file paths to upload, to get a ready-to-run command |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_yaml | string | yes | The full task YAML (a JSON object with the same fields also works) |
| models | array | yes | — |
| upload_uid | string | no | From prepare_attachments, so image and document tokens are counted |
| preset | string | no | Like the app's presets: standard = 2 passes + snappy timeouts (the default), thorough = 3 passes + patient timeouts. Explicit stability_runs / timeout_profile override it |
| stability_runs | integer | no | Passes per model; 2+ shows which models are consistent |
| max_tokens | integer | no | Output token limit per answer, 16 to 16000; 0 = no limit. Keep the default unless results show it was too low: a higher limit raises the credits needed to start. get_results flags models whose answers |
| temperature_discovery | boolean | no | Find each model's best temperature for this task. Costs about 6x as much |
| temp_preference | string | no | With temperature_discovery: which temperature wins a tie |
| timeout_profile | string | no | How long to wait per answer: snappy 45s, patient 90s, custom = custom_timeout |
| custom_timeout | integer | no | Seconds per answer, with timeout_profile custom |
| fail_fast | boolean | no | Stop a model after repeated errors to save credits. Set false to let every model finish, e.g. to diagnose failures |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_yaml | string | yes | The full task YAML (a JSON object with the same fields also works) |
| models | array | yes | Model ids from list_models |
| upload_uid | string | no | From prepare_attachments, when tests use attachments |
| max_credits | integer | no | Budget: if the expected cost is higher, nothing runs and you get the quote instead |
| preset | string | no | Like the app's presets: standard = 2 passes + snappy timeouts (the default), thorough = 3 passes + patient timeouts. Explicit stability_runs / timeout_profile override it |
| stability_runs | integer | no | Passes per model; 2+ shows which models are consistent |
| max_tokens | integer | no | Output token limit per answer, 16 to 16000; 0 = no limit. Keep the default unless results show it was too low: a higher limit raises the credits needed to start. get_results flags models whose answers |
| temperature_discovery | boolean | no | Find each model's best temperature for this task. Costs about 6x as much |
| temp_preference | string | no | With temperature_discovery: which temperature wins a tie |
| timeout_profile | string | no | How long to wait per answer: snappy 45s, patient 90s, custom = custom_timeout |
| custom_timeout | integer | no | Seconds per answer, with timeout_profile custom |
| fail_fast | boolean | no | Stop a model after repeated errors to save credits. Set false to let every model finish, e.g. to diagnose failures |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| optimize_for | string | no | accuracy (same order as the app's results table): best score, then cheapest, then fastest. cost / speed / stability: cheapest / fastest / most consistent model within tolerance points of the top sco |
| tolerance | number | no | Score points below the top score that still count as good enough |
| show_misses | boolean | no | List the tests each model got wrong, with the expected answer and the model's reply |
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.
No parameter schema on file.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | — |
| model | string | no | The model to keep as the pick (default: the best-scoring model). Use the model you recommended. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install OpenMark or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 23 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest06407966e9c4c2b6a5a9ce44cfecaf57c44a6bc6cc0427d097e6371e4fc26fd8
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_task_format | no tags | |
| validate_task | no tags | |
| list_models | no tags | |
| prepare_attachments | external-sink | external-sink: keyword "curl" |
| estimate_cost | no tags | |
| run_benchmark | no tags | |
| get_results | no tags | |
| get_account | no tags | |
| watch_task | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest06407966e9c4c2b6
Scanned2026-10-23
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish OpenMark can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.