Skip to main content
Glama

KeyVex

get_activist_stakes

Read-only

Returns Schedule 13D / 13G beneficial-ownership disclosures — filings made by anyone holding ≥5% of a class of registered equity securities. Each record is one reporting person on one filing (joint filings emit multiple rows under the same accession_number). Use this when the user asks about: who's accumulating large stakes, activist campaigns, takeover targets, hostile bids, or institutional concentration in a name. Also for 'who owns this company at the 5%+ level?' questions. Two flavors, distinguished by is_activist: - 13D (is_activist=true): filer signals INTENT TO INFLUENCE control. Activist campaigns, takeover stakes, hostile bidders. - 13G (is_activist=false): filer is PASSIVE. Mutual funds, advisers, banks, insurers, qualified institutional holders. Filter is_activist: true to see only the takeover-style filings — much higher signal-to-noise than the 13G firehose, which is dominated by routine quarterly disclosures from Vanguard, BlackRock, etc. COVERAGE FLOOR: KeyVex's ingestion of Schedule 13D/G filings begins January 2024. Filings before 2024 are not in the collection. A 13D/G query for activity in 2023 or earlier returns zero records — this is the collection's coverage boundary, not a per-entity gap. 13D/A and 13G/A AMENDMENT EXIT FILINGS: when a filer reports they have divested below the 5% threshold, the resulting row carries shares_owned: 0 and percent_of_class: 0. These rows are CORRECT — an exit IS zero — not missing data. To distinguish active stakes from exit filings, filter by shares_owned > 0 or by min_percent_of_class. ⚠ THIS TEXT USED TO SAY Item 4 WAS NOT AVAILABLE HERE. It is, as of 2026-08-28. Pass include_filing_narrative:true for the filer's own 'Item 4: Purpose of Transaction' — where board seats, consent rights and control intentions are actually declared — plus Item 2 (the ownership chain behind the filer), Item 2(d)-(e) (criminal and civil proceedings, as prose), Item 3 (source of funds) and Item 6 (the contracts with the issuer that implement Item 4). It is off by default only because it is long, not because it is missing: measured at 58.5% of a row. Rows holding withheld narrative say so via filing_narrative_available. 13D only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cusipNo9-character CUSIP of the security being reported on. Useful for cross-class filings (preferred vs common).
limitNoMaximum records to return. Default 50, max 500.
sinceNoISO date (YYYY-MM-DD). Only records on or after this date, using sort_by as the date field.
untilNoISO date (YYYY-MM-DD). Only records on or before this date.
tickerNoIssuer stock symbol filter, e.g. 'AAPL'. Case-insensitive.
sort_byNoField used for ordering and for the since/until date filters. Default: filing_date.
filer_cikNoFiler (reporting person) CIK. Exact match.
filer_nameNoFull or partial filer name; case-insensitive substring match. Example: 'BlackRock' matches all BlackRock entities.
sort_orderNoDefault: desc (most recent / largest first).
company_cikNoIssuer SEC CIK (10-digit, padded with leading zeros). Alternative to ticker.
filing_typeNoExact filing type. /A variants are amendments. Original 13D/G filings (no /A) signal a fresh crossing of the 5% threshold.
is_activistNoFilter to 13D filings only (true) or 13G only (false). Omit to include both. Use is_activist=true to surface takeover/activist signal.
min_percent_of_classNoFilter to filings where percent_of_class >= this value. Use to focus on large/concentrated stakes.
include_filing_narrativeNoInclude the Schedule 13D narrative items in each row: Item 2 (the reporting person and the ownership chain behind them), Item 2(d)-(e) (criminal convictions and civil securities proceedings in the last five years, as PROSE — usually a denial, never reduced to a flag), Item 3 (source of funds: own money vs borrowings), Item 4 (PURPOSE OF TRANSACTION — the filer's own statement of intent, where board seats, consent rights and control ambitions are declared) and Item 6 (the contracts with the issuer that implement Item 4). Default FALSE because these are long: measured at 58.5% of a row and ~548 KB on a 50-row page, and the same text repeats once per reporting person on a filing. Ask for it when researching WHY a stake was taken; leave it off when you want the numbers. Rows that have narrative available but withheld carry `filing_narrative_available: true`, so an absent field is never mistaken for a filer who said nothing. 13D only — 13G filings carry no narrative items.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover only the safe-read profile; the description carries everything else. It discloses the January 2024 ingestion floor and that pre-2024 queries return zero by boundary rather than entity gap, explains that 13D/A exit rows with shares_owned:0 are correct rather than missing data, and warns that include_filing_narrative adds ~58.5% to each row / ~548 KB per 50-row page. That is exactly the kind of behavior an agent cannot infer from structured fields.

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

Conciseness4/5

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

Front-loaded with the definition, then bolded subsections for 13D vs 13G, coverage floor, exit filings and the narrative flag, so a skimmer hits the decision-relevant facts first. It is long and the 'THIS TEXT USED TO SAY Item 4 WAS NOT AVAILABLE' passage is meta-commentary that costs space, but almost every other sentence earns its place.

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 14-parameter, no-output-schema research tool, the description supplies the domain frame (13D/13G semantics), the coverage boundary, the zero-value edge case, and the optional-heavy-field tradeoff — everything an agent needs to call it correctly and interpret empty or zero results. Nothing material is left to inference.

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 real meaning: is_activist is framed as the 13D-intent vs 13G-passive distinction, include_filing_narrative is explained item-by-item (Item 2/2(d)-(e)/3/4/6) with its cost and its 13D-only limitation, and min_percent_of_class is offered as the way to separate live stakes from exit rows. It stops short of adding syntax beyond the schema.

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

Purpose5/5

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

States a specific verb+resource ('Returns Schedule 13D / 13G beneficial-ownership disclosures'), defines the record grain (one reporting person per filing, joint filings emit multiple rows), and pins the 5% threshold that makes the data meaningful. An agent can distinguish this from get_institutional_holdings, get_insider_filings and get_proxy_filings without opening any schema.

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

Usage Guidelines5/5

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

Explicit when-to-use list ('who's accumulating large stakes, activist campaigns, takeover targets, hostile bids, institutional concentration'), plus the exact user phrasing it answers. It also names the internal alternative — filter is_activist:true for signal vs the 13G 'firehose' of routine Vanguard/BlackRock quarterly filings — which is a genuine routing decision.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources