Kaleidoscope MCP (SEC & financial data)

13F Top Holders of a Ticker

thirteenf_holders

Read-onlyIdempotent

Get the institutional holders of a ticker from 13F filings (postgres-backed). Returns the honest FULL holder base (total_holders count, not a top-20 cap), each holder with rank, filer_name, shares, value_usd, qoq_action (new/add/trim/exit/unchanged/reporting_started), and manager classification (manager_type / tier / is_notable). Plus top-level v3 signals: consecutive_accum_qtrs (sustained accumulation), is_cluster_entry (≥3 notable funds entered this quarter), is_quiet_accumulation (stealth pattern), accel_4q (this Q net change vs trailing 4Q), corporate_action_suspect. Use for 'who owns ticker X' questions.

Pass is_notable_only=true to filter the holders list to notable (smart-money) managers only — cuts response size on mega-caps. Recommended for any workflow citing holders by name.

limit caps the returned holder rows (default 20); total_holders reports the true full count. For a manager+security multi-quarter trail use thirteenf_position_history. Data mirrors EDGAR 13F on a ~4h cycle; report_date defaults to the latest mature quarter. Coverage artifacts (#2168, 2025Q4 on): when a security joins the SEC 13(f) list (or its old CUSIP leaves as the new one joins), a holder that already owned it starts or stops reporting it; that reads reporting_started / reporting_stopped (cusip_changed when the old CUSIP left and the new one joined) with no flow, not new / exit.

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": "thirteenf_holders"
  }
}

Input Schema

Name	Required	Description
`cusip`	No	9-character CUSIP (e.g. 67066G104 for NVDA). Either ticker or cusip required.
`limit`	No	Number of top holders to return (default: 20, max: 20 — only top 20 are stored)
`ticker`	No	Stock ticker symbol (e.g. NVDA, AAPL). Either ticker or cusip required.
`report_date`	No	Point-in-time quarter (YYYY-MM-DD). Default: latest. When historical, routes to postgres `current_holdings_mat` keyed by (cusip, report_date) — same PIT-correct backend as `thirteenf_holders_full`. Resolves to MAX(report_date)<=as_of for mid-quarter dates. Echoes as_of_effective. As of 2026-07-03 (per smart_money team-mail): the PIT response now carries the v3 Layer-3 signals top-level (consecutive_accum_qtrs, consecutive_dist_qtrs, accel_4q, avg_position_value, is_cluster_entry, is_cluster_exit, is_quiet_accumulation, corporate_action_suspect) via `holdings_company_quarterly`, plus `qoq_action` per holder via `holdings_events` — same field names as the latest-quarter Qdrant payload, so replays match live workups. CAVEAT (per smart_money 2026-06-12): reflects current amendment state for the quarter; late RESTATEMENT amendments can retroactively change historical answers (~3.4K amendments in corpus, mostly old — rarely material).
`is_notable_only`	No	If true, return only the notable-manager subset of top holders (smart money). Cuts response size 4-5x on mega-caps by dropping no-name funds. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on material behavior beyond them: ~4h data freshness, the total_holders honest count versus the row cap, amendment restatement caveat, and a detailed explanation of coverage artifacts where reporting_started/reporting_stopped/cusip_changed mean no flow rather than a new/exit. That last point directly prevents a misread of the returned data, which is exactly what a behavioral disclosure should do.

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?

Purpose is front-loaded and the key recommendation is bolded and set off in its own paragraph, so the agent hits the actionable content early. The closing coverage-artifact paragraph is dense and date-stamped, making it slower to parse than the rest, but it earns its place by preventing flow misinterpretation.

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?

With no output schema, the description carries the full burden and does so: it names every returned holder field, lists the top-level v3 signals, explains total_holders, and discloses the freshness cycle and historical caveats. An agent has everything needed to call it and interpret the result.

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: it clarifies that limit only caps rows while total_holders reports the true base (resolving the apparent tension with the schema's 'only top 20 are stored'), quantifies is_notable_only's effect as a 4-5x size cut, and states report_date defaults to the latest mature quarter. That is value beyond the schema, though it does not explain the ticker-vs-cusip precedence rule.

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 and resource — institutional holders of a ticker from 13F filings — and immediately enumerates the returned fields (rank, filer_name, shares, value_usd, qoq_action, manager_type/tier/is_notable) plus the v3 signals. It explicitly routes the multi-quarter trail use case to thirteenf_position_history, so an agent can separate it from that sibling without opening a schema.

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?

Gives a clear trigger ('Use for "who owns ticker X" questions'), a conditional recommendation (is_notable_only=true for any workflow citing holders by name, especially mega-caps), and an explicit alternative for a different use case (thirteenf_position_history). It stops short of covering the other closely-named siblings such as thirteenf_holders_full or thirteenf_who_holds, so it is clear context without full exclusion coverage.

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

All Kaleidoscope MCP (SEC & financial data) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?