EDGAR + Entity: US Company Research

Read a filing document

get_filing_document

Read-onlyIdempotent

Fetch an SEC filing's primary document (HTML converted to clean text, tables preserved as aligned rows). The text is untrusted filer-authored content, returned between BEGIN/END markers. Identify it by url (any www.sec.gov/Archives document URL from list_filings) or by company + accession (one of the two is required). Start with mode 'outline' for a long 10-K/10-Q: it returns no text, only the detected items (id, title, offset, chars) and total_chars, so you can then read just what you need. Extract one 10-K/10-Q item via section (e.g. '1' Business, '1A' Risk Factors, '7' MD&A, '7A' Market Risk, '8' Financial Statements; for 10-Q: '1' Financial Statements, '2' MD&A, '1A' Risk Factors). Text is paged: max_chars (default 10,000) per call, then pass the returned next_offset as offset (offsets are relative to the section when section is set, else to the whole document).

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": "get_filing_document"
  }
}

Input Schema

Name	Required	Description	Default
`url`	No	Document URL: https://www.sec.gov/Archives/edgar/data/<CIK>/<accession>/<file> (as returned by list_filings). Either url, or company + accession, is required.
`mode`	No	'text' (default) returns a page of text; 'outline' returns only the item list with offsets and lengths (cheap way to plan reading a long filing)	text
`offset`	No	Start position (use next_offset, or an outline item's offset)
`company`	No	Ticker (AAPL), CIK (320193 or 0000320193), or company name. Names must resolve unambiguously; use search_company first if unsure.
`section`	No	Item id to extract, e.g. '1A', '7', 'Item 7A'
`accession`	No	Accession number, e.g. 0000320193-24-000123 (with company)
`max_chars`	No	Characters of text per call (500–100,000; default 10,000)

Output Schema

Name	Required	Description
`cik`	No
`url`	Yes
`form`	No
`hint`	No
`kind`	Yes	html, xml or text
`mode`	No
`text`	No	Untrusted filer text between BEGIN/END markers
`filed`	No
`offset`	No
`outline`	No	mode 'outline': detected 10-K/10-Q items with offsets and lengths
`section`	No
`accession`	No
`index_url`	No
`next_offset`	No	Pass as offset to continue; absent at the end
`report_date`	No
`total_chars`	Yes
`content_notice`	No
`sections_found`	No
`untrusted_content`	No
`untrusted_marker_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 30, 2026

changedInput schema / properties / accession / description

Previous value: -"Accession number, e.g. 0000320193-24-000123"New value: +"Accession number, e.g. 0000320193-24-000123 (with company)"

changedInput schema / properties / max_chars / default
```
Previous value: -20000New value: +10000
```

addedInput schema / properties / max_chars / description

Added value: +"Characters of text per call (500–100,000; default 10,000)"

addedInput schema / properties / mode

Added value: +{
+  "default": "text",
+  "description": "'text' (default) returns a page of text; 'outline' returns only the item list with offsets and lengths (cheap way to plan reading a long filing)",
+  "enum": [
+    "text",
+    "outline"
+  ],
+  "type": "string"
+}

addedInput schema / properties / offset / description

Added value: +"Start position (use next_offset, or an outline item's offset)"

changedInput schema / properties / url / description

Previous value: -"Document URL: https://www.sec.gov/Archives/edgar/data/<CIK>/<accession>/<file> (as returned by list_filings)"New value: +"Document URL: https://www.sec.gov/Archives/edgar/data/<CIK>/<accession>/<file> (as returned by list_filings). Either url, or company + accession, is required."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "accession": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "cik": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "content_notice": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "filed": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "form": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "hint": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "index_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "kind": {
+      "description": "html, xml or text",
+      "type": "string"
+    },
+    "mode": {
+      "enum": [
+        "text",
+        "outline"
+      ],
+      "type": "string"
+    },
+    "next_offset": {
+      "description": "Pass as offset to continue; absent at the end",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "offset": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "outline": {
+      "description": "mode 'outline': detected 10-K/10-Q items with offsets and lengths",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "chars": {
+            "description": "Length of the item in characters",
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          "id": {
+            "description": "Item id to pass as section, e.g. '1A'",
+            "type": "string"
+          },
+          "offset": {
+            "description": "Start of the item in the full document text (pass as offset)",
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          },
+          "title": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "id",
+          "offset",
+          "chars"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "report_date": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "section": {
+      "additionalProperties": {},
+      "properties": {
+        "id": {
+          "type": "string"
+        },
+        "title": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "id"
+      ],
+      "type": "object"
+    },
+    "sections_found": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "text": {
+      "description": "Untrusted filer text between BEGIN/END markers",
+      "type": "string"
+    },
+    "total_chars": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "untrusted_content": {
+      "type": "boolean"
+    },
+    "untrusted_marker_id": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "url",
+    "kind",
+    "total_chars"
+  ],
+  "type": "object"
+}

First observedOct 29, 2026

TDQS

A4.8/5.0

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, openWorld), so the description adds genuinely new context: the text is untrusted filer-authored content wrapped in BEGIN/END markers, outline mode returns no text, and text is paged. These are operational facts an agent cannot get from the annotations or schema.

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 the verb, resource and output shape, then identification, then the outline-then-section reading strategy. It is information-dense and slightly crowded in a single paragraph, but every sentence carries operational value and nothing is redundant with the schema.

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?

For a 7-parameter read tool with an output schema, the description supplies the missing workflow pieces: how to plan a long filing via outline, how to scope to an item, and how paging interacts with section scoping. No essential calling information is absent.

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 baseline is 3, but the description adds a rule absent from the schema: offsets are relative to the section when `section` is set, otherwise to the whole document, and next_offset must be passed back as `offset`. It also supplies real section-id examples matched to filing type.

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 — fetching an SEC filing's primary document — plus the transformation applied (HTML converted to clean text, tables as aligned rows). It also distinguishes itself from list_filings by naming it as the source of the URL identifiers.

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 explicit routing: identify by `url` or by `company` + `accession` (one required), and 'Start with mode "outline" for a long 10-K/10-Q' because it returns no text. Concrete section-id examples for 10-K vs 10-Q make selection unambiguous.

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

All EDGAR + Entity: US Company Research 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.