Skip to main content
Glama
Signal8 MCP Server

Signal8 MCP Server

Official

Get Reverse Splits List

get_reverse_splits_list
Read-only

Retrieve cross-company reverse-split lists by view—upcoming, recent, approved without date, vote pending, or cancelled—with filters for market cap, security type, exchange, board authority, and domicile.

Instructions

The cross-company reverse-split lists the Signal8 Reverse Splits page serves, one view per call. view "upcoming" = splits with an effective date from tomorrow through 30 US market days ahead, the vendor market calendar union Signal8's SEC-filing tracker (filings, exchange and depositary notices); "recent" = the same union for effective dates in the past 30 days; "approved_no_date" = tracked episodes where shareholders (or the board, where no vote is required) have approved a reverse split but no effective date is stated yet; "vote_pending" = tracked episodes where a reverse split is proposed and the shareholder vote has not happened yet; "cancelled" = tracked episodes that ended without the split taking effect in the past 90 days (withdrawn by the company, a vote that did not approve it, an approved authority that expired unused, a meeting postponed indefinitely), with a cancelled object (outcome, outcomeLabel, endedOn, endedOnBasis, laterEpisode when the company has a newer open proposal) and the closing document as the source; older ended episodes are on the separate ended-reverse-splits tool. A security sits on exactly one of the first four views (upcoming, then recent, then approved_no_date, then vote_pending), with one exception: a split the company's own filing dates is on upcoming even when the same company also has a different, later split proposal awaiting a vote, which is then on vote_pending too; "cancelled" may repeat a company another view lists. Each row carries ticker, companyName, hasPage, source ("market_calendar" or "tracker"), stage + stageLabel, trackerState, ratio (or ratioMin / ratioMax for an authorised range), meetingDate, approvedDate, effectiveDate, effectiveDateSource, marketCalendarAgrees / marketCalendarDate / marketCalendarRatio, effectiveCondition, verification, marketConfirmation (recent only), marketCapUsd + capBucket, securityType, exchange, cik, sourceUrl / sourceAccession / sourceFormType / sourceFiledDate / sourceLabel, sourceDocuments (every document behind the episode), quote, adsRatioChange, approvalPath, domicile, splitAuthority and authorityTerms. Null means not measured or not stated: not "no split", not zero, not "no vote needed" and not "no date". A null ratio = the documents state none yet; a null marketCapUsd = cap not measured (capBucket is then null, not "nano"); a null verification = no tracked episode; a null domicile = not measured (not "Delaware"); a null marketConfirmation = the price step was not measured. An empty rows array on a view is normal and is not evidence that no company is splitting. completeness says what the view is: "scheduled_as_of_now" (upcoming) and "recorded_as_of_now" (recent) are what is known as of now, not "all reverse splits"; "tracked_episodes" is what the tracker has read from filings since it started, not every company. A scheduled split can still be postponed or cancelled: it is scheduled, not confirmed. Dates: effectiveDate is the scheduled effective date (vendor calendar, or the issuer-stated date strictly parsed from the filing); a filing or listing-rule deadline is not an effective date and does not appear in this field. A conditional date ("the 25th trading day after...") is returned verbatim in effectiveCondition and is not a date. effectiveDateSource says where effectiveDate came from: "filing" = the issuer stated it; "market_calendar" = the filing states no date and the vendor calendar supplies it. marketCalendarAgrees is a cross-check on a tracker row the calendar also lists: true = same date and ratio; false = at least one differs and marketCalendarDate / marketCalendarRatio hold the calendar's value (the filing's value is the row's value, and the two sources disagree); null or absent = not compared (no calendar row). meetingDate is the shareholder meeting date, not the split date. Approval and authority: approvalPath.path is shareholder_vote, written_consent, fpi_written_resolution, pre_approved_range (the board sets the ratio inside a range shareholders approved earlier), board_only (the issuer's own filing says no shareholder approval is required, quoted), depositary_ratio_change (an ADS ratio change by the depositary, no vote) or unknown ("Not determined", not "no vote"). splitAuthority.boardMayActWithoutVote is true only from the issuer's own filing or charter; a domicile default alone is not a finding. authorityTerms is the authority behind the episode: a cumulativeCap (the board may split in steps, each within the cap, without a new vote until the authority expires), multiStep, the expiry, and what executed splits already used; null = the documents state nothing beyond the ratio. Locked rows are withheld, not absent. The split facts on every view are part of Signal8 Pro. A caller whose API key is not owned by a Pro account gets every row with locked: true and only ticker, companyName, hasPage and exchange on it; the response then carries access: "preview", lockedCount (how many rows are locked) and rowLimit. A locked row means the facts exist and were not shown to this caller (they need Signal8 Pro); it does not mean "no split". access: "full" = every row carries its facts. filtersLimitedToUnlocked: true = a board / domicile filter was applied to unlocked rows only (locked rows are left out entirely, because matching them would reveal the fact through membership). Filters apply server-side: cap (scanner buckets), type (security type), exchange, board ("without_vote": board split authority on file, from the issuer's own filing or charter) and domicile. Each accepts "not_measured" to select rows where that fact was not measured; an unmeasured row never matches a measured bucket. totalCount is the filtered list (locked rows included), unfilteredCount the view before filters, capUnknownCount the rows whose cap was not measured (on the calendar views). Paging uses limit / offset; truncated: true = more rows exist. available: false with reason "tracker_not_enabled" (the three tracker views) means the tracker is switched off, not that nothing is pending. An HTTP 503 FEATURE_DISABLED means the page is switched off, and the response then says nothing about any company's split. The data describes what is on file and carries no view on whether a split will happen, what it means for the price, or what anyone should do.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_reverse_splits_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
capNoMarket-cap buckets to keep (the premarket scanner's): nano, micro, small, mid, large, or not_measured for rows whose cap was not measured. Empty = every row.
typeNoSecurity types to keep: common, adr (ADR / ADS), ordinary (foreign ordinary shares), other, or not_measured. Empty = every row.
viewNoWhich list: "upcoming" (effective tomorrow through 30 market days ahead; the calendar UNION the tracker), "recent" (effective in the past 30 days), "approved_no_date" (approved, no effective date stated yet), "vote_pending" (proposed; the shareholder vote has not happened), "cancelled" (ended without taking effect in the past 90 days). Default "upcoming".upcoming
boardNo["without_vote"] keeps only rows whose issuer can split without a shareholder vote on the evidence of its OWN filing or charter (a domicile default never matches). Pro-only fact: on a non-Pro key it applies to unlocked rows only.
limitNoRows per page, 1 to 200 (default 50).
offsetNoRows to skip (default 0). Locked rows count towards paging.
domicileNoRegistrant domicile groups to keep: bvi, nevada, cayman, marshall_islands, bermuda, delaware, other, or not_measured. Pro-only fact: on a non-Pro key it applies to unlocked rows only.
exchangeNoListing venues to keep: NASDAQ, NYSE, AMEX (NYSE American), OTC, or not_measured. Empty = every row.

Output Schema

NameRequiredDescriptionDefault
dataNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.20.0

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/non-destructive/closed-world; the description adds substantial behavior an agent cannot infer: Pro-gating with locked rows and access='preview', lockedCount, rowLimit, filtersLimitedToUnlocked, truncated, totalCount vs unfilteredCount, available:false with reason 'tracker_not_enabled', and HTTP 503 FEATURE_DISABLED meaning. It also defines what null means for each field so nulls are not misread as 'no split' or 'zero' — exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is largely substantive, but it is delivered as one enormous undifferentiated block covering views, row fields, null semantics, approval paths, Pro gating, filters, counts, paging and error states. There is no paragraphing, list structure or grouping, so an agent must parse roughly 800 words linearly to find the one view definition it needs; the return-field enumeration is also largely duplicated by the existing output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-view, heavily filtered, entitlement-gated list tool, almost nothing an agent needs to call it correctly is missing: view selection, null interpretation, locked-row behavior, filter semantics, pagination, counts and disabled-feature responses are all covered. An output schema exists, yet the extra explanation of row fields is additive rather than redundant because it explains null semantics rather than shapes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: the distinction between capUnknownCount and an unmeasured cap, the rule that an unmeasured row never matches a measured bucket, the board filter being sourced only from the issuer's own filing or charter (never a domicile default), and the Pro-only filtering caveat on board/domicile. Paging semantics (locked rows count towards paging) are also clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific resource (the cross-company reverse-split lists) and a specific access pattern (one view per call), then defines all five view values with concrete date windows and inclusion rules. It routes 'older ended episodes' to the separate ended-reverse-splits tool, but never mentions the sibling get_upcoming_reverse_splits, leaving overlap between the 'upcoming' view and that tool unresolved.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is spelled out per view: what qualifies for 'upcoming' vs 'recent' vs 'approved_no_date' vs 'vote_pending' vs 'cancelled', including the one-security-one-view rule and the exceptions. It also documents filter semantics (server-side, 'not_measured' selecting unmeasured rows, unmeasured never matching a measured bucket) and points to the ended-reverse-splits tool for older episodes. No explicit exclusion versus get_upcoming_reverse_splits, which is the main gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools