Skip to main content
Glama
Sign In
Finance MCP

Finance MCP

by Blahaj-gif
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Get Edgar Filings

get_edgar_filings
Read-onlyIdempotent

Search, list, or monitor SEC EDGAR filings by ticker, full-text phrase, or live form-type feed; returns recent 8-K, 10-Q, 10-K, Form 4 and other filings with SEC acceptance timestamps.

Instructions

SEC EDGAR filings, as close to real time as a public feed allows — timestamps carry the second the SEC accepted the document.

Three modes, chosen by what you pass:

  • symbol set → that company's recent filings (earnings 8-Ks, 10-Q, 10-K, Form 4).

  • query set → full-text search across filing bodies, 2001-present.

  • neither → the live firehose of form_type filings from every registrant.

This lists and finds filings; it does not open them. To read a section out of one, use read_filing; for the headline numbers as XBRL facts, use get_company_financials.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum rows to return (default 15).
queryNoFull-text phrase to search for (e.g. "going concern", "tariff").
symbolNoTicker to scope to (e.g. MU, AAPL).
form_typeNoFiling type — 8-K, 10-Q, 10-K, 4, S-1, 13F-HR. Comma-separate for several.8-K

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.1
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "type": "object",
-  "x-fastmcp-wrap-result": true
-}New value: +null
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: near-real-time freshness with second-level acceptance timestamps, and the 2001-present backfill window for full-text search. It stops short of describing result ordering or pagination limits, which keeps it at 4.

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 the resource and freshness claim, then a scannable three-bullet mode block, then a one-line boundary statement. No sentence is redundant and the structure mirrors how an agent decides which call to make.

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 4-parameter read tool with no output schema, the description covers mode selection, freshness, coverage window, and boundaries versus siblings. The one gap is the shape of returned rows (identifiers, fields available for follow-up calls to read_filing), which an agent must infer.

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 each parameter is already documented individually, which sets the baseline at 3. The mode-routing paragraph does add interaction semantics the schema lacks — notably that omitting both symbol and query yields a firehose scoped only by form_type — but it doesn't clarify precedence when symbol and query are both supplied.

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 ('SEC EDGAR filings... lists and finds filings') and enumerates three distinct operating modes. It explicitly distinguishes itself from the two most confusable siblings (read_filing, get_company_financials), so an agent can choose 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 Guidelines5/5

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

Gives an explicit parameter-to-mode routing table: symbol set → company filings, query set → full-text search 2001-present, neither → live firehose. It also states the negative case ('does not open them') and names the correct alternatives for that need.

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