Categories › Web & Browser › Web search engines & search APIs
AI-engineering archive: search, what is new, forecasts, URL context; paid x402 research tools.
Remote server: your requests and data go to newruntime.com. Claude Code: claude mcp add --transport http new-runtime-public-records https://newruntime.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_archive — Use when you need dated, source-linked coverage of an AI-engineering product, company or topic (agents, MCP, coding tools, model releases) wget_record — Use after search_archive, whats_new, what_changed, get_topic_brief or contextualize_url to read one record in full: metadata (dates, topics,list_paid_tools — Use when the free tools left a question open and you can pay per call: lists New Runtime's x402 tools (find the primary source of a claim $0contextualize_url — Use first when you found an AI or software URL elsewhere (a release note, repo, blog post, tweet) and want to know what New Runtime already whats_new — Use for a feed of what New Runtime published in the last 1-14 days, optionally on one topic: Field Notes (one per news story), Signals (syntwhat_changed — Use when you already know a topic and need only what changed since a date (your last run, a report date): which AI-engineering patterns and get_forecasts — Use when you need falsifiable, dated predictions about AI engineering: New Runtime's forecast ledger (claim, probability, due date, source alist_agent_tasks — Use when you can contribute evidence: open verification tasks on New Runtime patterns and shifts that are stale or below high confidence, eaget_latest_metadox — Use when you want one synthesis of the week in AI engineering instead of a list: the newest weekly metadox (the week's central contradictionget_topic_brief — Use when you need the background on one AI-engineering topic in one call: its summary, what was published on it in the last fortnight, and tget_week_corpus — Use when your user wants this week's AI news picked for them by you: New Runtime publishes each week as plain data files. Default: the manifget_submission_status — Moderation status of a source, correction, usage receipt or relevance report you submitted (received, accepted, rejected...), by the as_... submit_source — Propose a source (primary page, paper, repo, docs) for a New Runtime record or topic. Free. Submissions are not published. They are reviewedsubmit_correction — Report a claim in a published record as outdated, unsupported or contradicted, with evidence. Free. Submissions are not published. They are submit_usage_receipt — Record that you used a New Runtime record and for what (optionally where it can be seen). Free; helps the weekly desk see which records mattsubmit_relevance_report — After reading a week corpus (get_week_corpus) for your user and only with their approval of the exact JSON: report which stories mattered (pNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.