Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

M&A Screen (by industry / deal value / status) [beta]

mars_mergers_screen
Read-onlyIdempotent

Cross-company M&A screener with filters: date range, industry, minimum deal value, status ('announced'/'completed'/'terminated'/'regulatory_review'). Returns acquirer + target (name, company_id, ticker), announcement_date, deal_value_usd, status, industry, merger_type, strategic_goals, source article URL + snippet, published_at. Source: Mars-resolved mergers from wire services.

v2 (mars-v2 methodology, 2026-06-17): substrate swapped to UUID-keyed company_id. acquirer/target UUIDs surface when known (chain-able). Multi-wire duplicate rows collapse on demand via dedupe=true (keyed on (acquirer_company_id, target_company_id, announcement_date) — UUID-based so trivial name variants collapse correctly).

IMPORTANT: industry is grok3-extracted free-text and drift-prone — for thematic slices use mars_search_articles. deal_value_usd is NULL for undisclosed deals (~40% of small M&A). Status values per v2: 'announced' / 'completed' / 'terminated' / 'regulatory_review' (lowercase). Mars covers both private and public-company M&A. Each deal row carries accession + filing_url (the merger agreement's filing, when one is linked; open with get_filing) and accessions (every SEC filing linked to the deal, max 10); both are empty for news-only deals.

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": "mars_mergers_screen"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax mergers (default 200, max 1000).
dedupeNoLegacy no-op — merger_deals_v2 is already deal-grain (one row per deal). Kept for back-compat.
statusNoDeal status: 'announced' | 'completed' | 'terminated' | 'regulatory_review' (lowercase).
date_toNoISO date upper bound (default open-ended).9999-12-31
industryNoExact-match industry (free-text, drift-prone — prefer mars_search_articles for thematic).
date_fromNoISO date lower bound on announcement_date (default '2023-01-01').2023-01-01
min_valueNoMinimum deal_value_usd (USD).
include_warnsNoInclude integrity_tier 'reported' (single secondary news report) and 'warn' rows (known extraction bugs — trillion-dollar misparses, self-mergers, sentinel names). Default false (only verified+vouched).
is_definitiveNoFilter to REAL deals only — deal_stage IN (definitive, pending, closed), excluding rumor/talks/loi/terminated. The 'how much is real vs rumor' filter (mars 2026-07-26; hits a partial index). Default: no filter (returns all stages). Each row also carries `deal_stage` + `is_definitive` so you can see the finer ladder.
min_freshnessNoFilter to deals mars saw at-or-fresher-than this class (by first_seen_at): fresh <7d / recent <30d / aging <90d / stale = no filter. Every row carries `first_seen_at` + server-computed `days_since_first_seen` + `freshness_class` so you can judge staleness before trading on it. For the tightest Kalshi ACQ filter: is_definitive=true + min_freshness='fresh'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
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 adds substantial context beyond them: provenance (Mars-resolved wire-service mergers), the ~40% NULL rate on `deal_value_usd` for undisclosed deals, the integrity-tier gating behind `include_warns`, and the fact that each row carries `accession`/`filing_url`/`accessions` for chaining into `get_filing`. That is exactly the kind of data-quality disclosure a screening tool needs.

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

Conciseness3/5

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

The purpose and return-field inventory are front-loaded and efficient, but the middle is a dense v2 changelog ("substrate swapped to UUID-keyed company_id", version dates) that reads like release notes rather than agent guidance. The `dedupe` discussion in particular spends several lines on a parameter the schema calls a no-op, so not every 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?

With no output schema, the description carries the return-shape burden itself and does so thoroughly: acquirer/target name, company_id and ticker, announcement_date, deal_value_usd, status, industry, merger_type, strategic_goals, source URL/snippet, plus the filing linkage fields. It also flags the two traps an agent would otherwise hit (NULL deal values, drift-prone industry strings), so nothing essential is missing for a 10-parameter screen.

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

Parameters2/5

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

Schema coverage is 100%, so the baseline would be 3, but the description actively muddies one parameter: it says multi-wire duplicates "collapse on demand via `dedupe=true` (keyed on `(acquirer_company_id, target_company_id, announcement_date)`)", while the schema labels `dedupe` a "Legacy no-op — merger_deals_v2 is already deal-grain". An agent cannot tell whether to set it. Other parameters are merely restated from the schema rather than enriched.

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?

Opens with a specific verb+resource ("Cross-company M&A screener") and enumerates the filter axes (date range, industry, min deal value, status). It also carves out the boundary against a sibling by declaring that thematic/industry-drift slicing belongs to `mars_search_articles`, so an agent can pick between the two without opening either 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?

Provides real routing guidance: use `mars_search_articles` for thematic slices because `industry` is drift-prone, and use `is_definitive=true` when the question is "real deal vs rumor". It even supplies a named filter recipe (`is_definitive=true` + `min_freshness='fresh'`) for tight event screening. No explicit when-not for the company-scoped sibling (`mars_mergers_for_company`), which keeps it short of a 5.

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