Skip to main content
Glama

Sec Contracts Search

sec_contracts_search
Read-onlyIdempotent

Find SEC material-contract exhibits by CLAUSE LANGUAGE, credit agreements, merger agreements, indentures, employment and severance agreements, change-of-control agreements, license and supply agreements, warrants, searching the full text of every Exhibit 10 / Exhibit 4 / Exhibit 2 attached to 8-K, 10-K, 10-Q, S-1 and S-4 filings in SEC EDGAR full-text search (2001 to today). The inverted question: "credit agreements filed since 2025 with a change of control clause", "employment agreements with a 2x severance multiple", "indentures with a make-whole redemption", "merger agreements with a reverse termination fee". Returns one row per exhibit document: company, CIK, ticker, root form, filing date, exhibit type (EX-10.1, EX-4.2...), the filer's exhibit description ("EX-10.1 CREDIT AGREEMENT"), a text snippet around the matched phrase, the exhibit document URL, accession number and the filing index page, plus the same hits grouped by filing with each filing's exhibit list. Narrow by exhibit family (EX-10 material contracts, EX-4 debt instruments/indentures/warrants, EX-2 merger and acquisition agreements), root form, filing-date window, one company (name, ticker or CIK) or SIC industry code (7372 software, 2834 pharma, 6022 banks). Feed document_url (or adsh + filename + cik) to sec_contract_text to read the agreement.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 12,
      "query": "change of control",
      "since": "2025-01-01",
      "exhibit_type": "EX-10"
    },
    "name": "sec_contracts_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
sicNoRestrict to an SIC industry code, e.g. "7372" (prepackaged software), "2834" (pharmaceutical preparations), "6022" (state commercial banks), "1311" (crude petroleum and natural gas). Comma-separate several.
formNoRoot form the exhibit was attached to, e.g. "8-K", "10-K", "10-Q", "S-1", "S-4", "DEF 14A". Comma-separate several: "8-K,10-K". Omit for all forms.
limitNoMax exhibit documents to return (1-50, default 10). Each returned exhibit costs one bounded document read for its snippet when include_snippets is on.
matchNophrase (default): the words must appear together in order. all: every word must appear somewhere in the document. any: at least one word. Use `all` for concept searches like "severance multiple change control".
queryYesThe clause or phrase to find in exhibit text, e.g. "change of control", "make-whole", "reverse termination fee", "most favored nation". Multi-word input is matched as an exact phrase by default (see `match`). Double quotes inside the value are passed through, so "\"change of control\" severance" searches the phrase AND the word.
sinceNoEarliest filing date, YYYY-MM-DD. Full-text coverage starts 2001-01-01; earlier values are clamped. Default: 2 years before today.
untilNoLatest filing date, YYYY-MM-DD. Default: today.
companyNoRestrict to one filer: ticker ("ADBE"), company name ("Adobe") or CIK ("796343"). Names are resolved against the SEC ticker list first; unlisted names fall back to EDGAR's entity-name filter.
exhibit_typeNoExhibit family to keep. EX-10 = material contracts (credit, employment, license, supply, leases). EX-4 = instruments defining security-holder rights (indentures, notes, warrants, registration rights). EX-2 = plans of acquisition, reorganization, merger. EX-99 = additional exhibits (press releases, investor decks). any (default) = EX-10 + EX-4 + EX-2, the material-contract set. all_exhibits = every EX-* document. "10", "ex10" and "EX-10.1" are all read as EX-10.
include_snippetsNoFetch each matched exhibit and return a ~440-character window around the first occurrence of the phrase. Default true. Set false for a faster list-only answer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, open-world, idempotent and non-destructive, so safety is covered. The description adds non-obvious behavior beyond that: the one-exhibit-per-document result granularity plus a filing-grouped view, the snippet cost model ('each returned exhibit costs one bounded document read... when include_snippets is on'), default limit 10 / max 50, and that pre-2001 dates are clamped. Ordering and pagination semantics are not stated, which holds it below a 5.

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 purpose, then query examples, then narrowing facets, then return shape, then the handoff — a sensible order. The middle is a long run-on sentence enumerating every returned field, which is dense but earns its place because there is no output schema to carry that information.

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

Completeness4/5

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

For a 10-parameter, no-output-schema tool the description is close to self-sufficient: it discloses result granularity, the fields returned, snippet behavior, date coverage and clamping, cost per result, and the follow-up call. What is missing is minor — result ordering and how the grouped-by-filing view relates to `limit`.

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; the description still adds meaning by casting the search as 'the inverted question' and supplying clause-language exemplars ('make-whole redemption', 'reverse termination fee') plus the family semantics of EX-10 / EX-4 / EX-2 that tell an agent how to choose exhibit_type. The `match` mode behavior (phrase vs all vs any and when to prefer `all`) is explained conceptually as well as in 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?

Opens with a specific verb and resource: 'Find SEC material-contract exhibits by CLAUSE LANGUAGE', then enumerates the agreement categories (credit, merger, indenture, employment/severance, change-of-control, license/supply, warrants) and the exact filing universe (Exhibit 10/4/2 on 8-K, 10-K, 10-Q, S-1, S-4, full-text 2001 to today). The sibling sec_contract_text is explicitly positioned as the read step rather than a competing search.

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 concrete motivating queries ('credit agreements filed since 2025 with a change of control clause') and names the narrowing dimensions an agent should use (exhibit family, form, date window, company, SIC). It also routes to sec_contract_text for full reading, but gives no explicit exclusion — e.g. when to prefer sec_contracts_by_company — leaving that inference to the agent.

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.