Skip to main content
Glama
brechanbech

SEC EDGAR MCP

by brechanbech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Remote

Company XBRL Facts

sec_company_facts
Read-only

List a company's XBRL concepts and labels to find the correct metric name before querying financial values; narrow results with a query filter and paging.

Instructions

List the XBRL concepts (metrics) a company reports, to find the right name before querying values with sec_financial_concept. Each row gives the concept, its label and 'latest', the most recent period end with data: prefer a concept that is still current, since companies change tags (Palantir reports revenue as RevenueFromContractWithCustomerExcludingAssessedTax, not Revenues). Narrow with 'query' (matches name or label, e.g. 'revenue' or 'lease'). Returns 100 by default; 'matched' says how many fit, and passing 'next_offset' back as 'offset' fetches the next page. Descriptions are left out unless include_descriptions is set.

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of concepts to return (default 100, max 300)
queryNoOptional filter: match against concept name or label (case-insensitive substring), e.g. 'revenue', 'lease', 'OperatingActivities'
offsetNoNumber of matching concepts to skip, for paging (default 0). Pass the previous response's 'next_offset'.
tickerYesStock ticker, e.g. AAPL, or the company's CIK, e.g. 1163302, for one with no current ticker (delisted, acquired or renamed)
taxonomyNoTaxonomy to list: 'us-gaap' (default), 'ifrs-full', 'dei', or omit to list allus-gaap
include_descriptionsNoInclude each concept's full XBRL description (default false). They run to hundreds of characters each, so narrow with 'query' first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.7.0
    • addedInput schema / properties / include_descriptions
      Added value: +{
+  "default": false,
+  "description": "Include each concept's full XBRL description (default false). They run\nto hundreds of characters each, so narrow with 'query' first.",
+  "type": "boolean"
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "default": 100,
+  "description": "Number of concepts to return (default 100, max 300)",
+  "format": "uint64",
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Number of matching concepts to skip, for paging (default 0). Pass the\nprevious response's 'next_offset'.",
+  "format": "uint64",
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Optional filter: match against concept name or label (case-insensitive\nsubstring), e.g. 'revenue', 'lease', 'OperatingActivities'",
+  "type": "string"
+}
    • changedInput schema / properties / ticker / description
      Previous value: -"Stock ticker symbol"New value: +"Stock ticker, e.g. AAPL, or the company's CIK, e.g. 1163302, for one with no\ncurrent ticker (delisted, acquired or renamed)"
  2. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real value beyond that: default page size of 100, the 'matched' total, and the next_offset->offset paging loop, plus the fact that descriptions are omitted unless requested. It does not state row ordering or what a concept with no recent data looks like, so it is solid but not rich.

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

Conciseness5/5

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

Front-loaded with purpose and the downstream call, then narrowing, then paging, then the descriptions caveat. The Palantir parenthetical is long but teaches the failure mode that motivates the 'latest' check, so it earns its space.

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?

There is no output schema, and the description compensates by describing the returned row shape (concept, label, latest) and the paging envelope ('matched', 'next_offset'). Combined with the 6-parameter schema, an agent has everything needed to call and paginate correctly.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all six parameters, and the description largely restates them. It does add semantic value for 'query' (matches name OR label, case-insensitive, with realistic examples) and for the offset/next_offset handshake, which is a response-field contract absent from the schema. That lifts it slightly above the baseline but not far.

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 (list the XBRL concepts a company reports) and frames it as a discovery step whose output feeds sec_financial_concept. An agent can distinguish it from sec_financial_concept (values) and sec_xbrl_frames (cross-company) 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 ordering guidance: call this first to find the concept name, then query values with sec_financial_concept. Adds the practical rule to prefer concepts whose 'latest' is current, with a concrete warning that tag names drift (Palantir's revenue concept), plus when to use 'query' and when to enable include_descriptions.

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