Drive MCPJam's hosted eval tools end to end — check what a run will cost and disclose, launch it, poll it to a verdict, and triage a failure down to the step that failed. Use when connected to MCPJam's MCP server and asked to run, re-run, investigate, or…
Interpret and use `mcpjam` probe, doctor, OAuth, XAA (Cross-App Access / ID-JAG), apps conformance, tools, resources, and prompts output conservatively against MCP 2025-11-25. Use when interacting with MCP servers, executing tools, triaging findings,…
Find what happened in production using the Sentry, Axiom and PostHog MCP servers, and map it back to inspector code. Use for alert triage, a Sentry issue, an Axiom monitor, a spend or usage question, or "which user/org was this".
Start the MCPJam Inspector locally, sign the browser in, and check a change in the running app with screenshots. Use for any UI change and whenever a fix needs to be seen working, not only tested.
Diagnose and fix a failing GitHub Actions check on an MCPJam PR by mapping the failed job to the local command that reproduces it. Use when a PR check is red.
Rules for changes to the inspector's Hono server (mcpjam-inspector/server), including routes, services, logging, error reporting and the browserd daemon. Use before editing anything under mcpjam-inspector/server.
Rules for any change to MCPJam's UI (inspector client, design-system, chat-ui, widget-react, docs styling). Use before editing a .tsx component, a stylesheet, or design tokens.
Run the checks CI will run on the files you changed in the MCPJam monorepo, before opening or updating a PR. Use after any code change and before every push.
Review or write the short copy a user sees in MCPJam (errors, toasts, empty states, tooltips, labels). Names the slop pattern in each string and gives the fix, or rewrites a string so it says what happened and what to do next. Use before a PR adds or changes…
Drive an API Playground session through MCPJam's remote MCP tools or cloud CLI, inspect browser evidence, and hand the live session to its owner. Use for agent-driven MCP server debugging with a hosted browser.
Defines every member of MCPJam's user-value chain vocabulary — the six stages, the five stage states, the twenty-nine stage reasons, the seven failure categories, the four verdicts, the stage-analytics exclusion classes, the five friction signals and the nine…
Convert an existing test corpus (promptfoo YAML, pytest, Jest, CSV) into an MCPJam eval suite file at .mcpjam/evals/*.yaml, stamping every case with an honest import status, then validate it offline with `mcpjam cloud eval validate` until it exits 0. Use when…
Convert MCPJam Explore-generated test cases into @mcpjam/sdk eval tests. Produces one test per case, exactly matching the user's prompts and expectations.