Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Recently observed → Live
Live → Recently observed
Recently observed → Live
Live → Recently observed
Added "get_company_watchlist" (13 tools before, 14 now)
Company research watchlist — Latest model revisions, current review status and qualified checkpoints for 1-20 companies. No list is saved on the server. Compare revisions with your own last-seen markers. This reads published research, not new source checks or live quotes. Preserve unavailable rows.
Added "check_company_forecasts", "compare_company_history", "compare_company_revisions" and 3 more (7 tools before, 13 now)
Company forecast accountability — Compare frozen revenue forecasts with reported results. Forecasts must precede quarter end. Missing results and definition mismatches remain unavailable. This is not market-memory calibration.
Compare reported company quarters — Two to six companies, one quarter end (YYYY-MM-DD), USD history and provenance. Mismatched source concepts or missing history never become comparable numerical values.
Company revision changes — Compare facts, assumptions, scenarios and thesis between immutable revisions. Omit to_revision for latest.
Company revision history — Browse immutable published versions, reasons and pinned JSON/CSV links. Follow next_offset.
Added "get_company_file" and "list_coverage" (5 tools before, 7 now)
Company file — One covered company's living research file (company_file.v1): business, three drivers, the last eight fiscal quarters from SEC XBRL with provenance on every number, the desk's own estimates and revision log, the thesis and what changes it, the market-memory bands or an explicit coverage 'none', published notes, and the scorecard. symbol is a stock ticker; optional as_of (YYYY-MM-DD) returns the latest revision at or before that date, never a later one. Optional research and operating_model blocks include dated reviews, countercases, checkpoints, sourced actuals, managemen…
Research coverage — The research hub's coverage universe: clusters and symbols, with each symbol's company-file revision, as_of date, whether a compiled file exists, and skeleton=true when the authored half is empty. file=true is not coverage. No arguments. Read a file with get_company_file(symbol).
Certificate changed, valid to 2026-12-15
Changed the definition of "market_state"
⟨31 unchanged words⟩ Preserve status, sample sizes, dates, informative receipts, meta.warnings and meta.context_quality (missingvalues.tape fields, descriptive industry label and provenance). Vendor classification history is unverified; do not treat it as a historical sector or a condition on the matches. Excess ranges describe historical percentage-point returns relative to ⟨14 unchanged words⟩
Changed the definition of "read_research"
Read a publication ID returned by search_research, preserving its evidence. source_fields returns exact catalog status/receipt fields; content.source_rows exposes literal result tables/mappings with source positions and heading scope. These are source projections, not AI conclusions. Missing parsed rows do not establish absence of a result. Use the text/guide for interpretation and limits. overview returns findings, dates, samples, limitations, ⟨110 unchanged words⟩
Certificate recorded, valid to 2026-12-06
Authorization not required
First tool surface recorded: 5 tools (server version 1.29.1)
Showing the latest 13 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Company research status — Current monitoring alongside the immutable company file. Preserve scan versus review clocks, pending discovery leads, source failures and limitations. Never use current monitoring as historical evidence or as approval to promote a company. No arguments other than a ticker.
Try company assumptions — Calculate a temporary scenario from 1-20 assumption cell IDs and numerical values in their published units. Read get_company_file first. Reported facts, guidance and the published revision stay unchanged. Preserve limitations and identify user assumptions. No recommendation or valuation is implied.