EdgarTools
About
Open-source SEC EDGAR toolkit. 11 tools and 7 research prompts covering every major filing type — 10-K, 10-Q, 8-K, Form 4 insider trades, 13F institutional holdings, Form D private placements, Form ADV investment advisers, DEF 14A proxy statements, SC 13D/G ownership, and NPORT f
Details
- Author
- dgunning
- Downloads
- 379
- Categories
- Other, Finance
Jump to
- XBRL-native financial statements with standardized labels
- 20+ parsed filing types (10-K, 8-K, 13F, Form 4, etc.)
- Insider transaction tracking (Form 3/4/5)
- Institutional holdings and fund portfolio data
- Smart caching and configurable rate limiting
- Built-in MCP server for AI agent integration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
EdgarToolsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with pip install edgartools, set your identity with set_identity("your.email@example.com"), then use the Company and get_filings objects to retrieve and parse filings as typed Python objects, DataFrames, or LLM-optimized text.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"edgartools": {
"edgartools": {
"command": "uvx",
"args": [
"edgartools",
"--mcp"
],
"env": {
"EDGAR_IDENTITY": "Your Name your.email@example.com"
}
}
}
}
}
McpServers
{
"edgartools": {
"command": "uvx",
"args": [
"edgartools",
"--mcp"
],
"env": {
"EDGAR_IDENTITY": "Your Name your.email@example.com"
}
}
}
Why EdgarTools?
EdgarTools turns SEC filings into Python objects. Every supported form type gives you structured data — not raw HTML, not XML, not JSON dumps. Actual Python objects with properties, methods, and DataFrames.
<table align="center">
<tr>
<td align="center" width="33%">
<br>
<b>Fast</b><br>
Optimized with lxml & PyArrow<br>
Smart caching, rate-limit aware
</td>
<td align="center" width="33%">
<br>
<b>AI Ready</b><br>
Built-in MCP server for Claude<br>
LLM-optimized text extraction
</td>
<td align="center" width="33%">
<br>
<b>Well Tested</b><br>
1000+ verification tests<br>
Type hints throughout
</td>
</tr>
<tr>
<td align="center" width="33%">
<br>
<b>XBRL Native</b><br>
Full XBRL standardization<br>
Cross-company comparisons
</td>
<td align="center" width="33%">
<br>
<b>20+ Filing Types</b><br>
Typed objects for every form<br>
Pandas-ready DataFrames
</td>
<td align="center" width="33%">
<br>
<b>Open Source</b><br>
MIT license, free forever<br>
No API keys, no rate limits
</td>
</tr>
</table>
<p align="center">
</p>
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



