Remote MCP server that lists published Clearbar verdicts on the cheapest LLM that still passes a quality bar for a given task, with cost per successful task.
What you can do
List published verdicts, optionally filtered by task type, showing the task, pass bar, cheapest passing model, cost per successful task and the page to check it
Fetch the full verdict for one task by slug: pass rate, cost per successful task in US dollars, the baseline model, every candidate's status, and links to the verdict page, run file and re-run script
Report measured figures from public datasets with retries and failures counted, including a dated price snapshot
When to use it
Useful when choosing which model to run for a specific task and wanting a cost-versus-quality comparison rather than raw benchmark scores, or when checking whether a cheaper model clears an existing quality bar.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared, and no authentication is declared.
Before you install
Verdicts are published measurements on public datasets with a dated price snapshot, so costs may not match current pricing or your own data; the server only reads published verdicts and does not run evaluations on your examples.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.grain64.clearbar%2Fverdicts/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
List verdicts: which model is cheapest for each task
Which LLM is the cheapest that still passes? Lists every published Clearbar verdict: the task, the pass bar, the cheapest passing model, its cost per successful task (retries and failures counted) and the page to check it. Optional filter by task type.
Parameterstask
get_verdict
Get one verdict: cheapest passing model, cost, failures
The full verdict for one task: the cheapest model that clears the bar, its pass rate and cost per successful task in US dollars, the baseline model it is compared with, every candidate's status, plus links to the verdict page, the run file (JSON) and the script that re-runs it. Get the slug from list_verdicts.
Parametersslugrequired
Version history
1
v1.0.0LatestNov 6, 2026
Score
72%
72% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Publish an icon in the registry entry.
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.