Edgar MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install edgar-mcp
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add -e "EDGAR_API_KEY=${EDGAR_API_KEY}" edgar-mcp -- node "<FULL_PATH_TO_EDGAR_MCP>/dist/index.js"

Replace <FULL_PATH_TO_EDGAR_MCP>/dist/index.js with the actual folder you prepared in step 1.

Required:EDGAR_API_KEY+ 2 optional
README.md

SEC EDGAR financial data for your AI agent.

edgar-mcp

SEC EDGAR financial data for your AI agent.

What your AI can do

  • get_filings: fetch filing metadata (10-Q/10-K/8-K earnings release references)
  • get_financials: fetch full period facts (inline JSON or local file output)
  • get_metric: fetch a specific metric/tag for a period
  • list_metrics: list candidate metrics/tags in a filing period
  • search_metrics: fuzzy-search metrics by natural-language query
  • get_filing_sections: extract filing narrative sections/tables (10-K/10-Q default, or 8-K earnings release with source="8k")

Install

pip install edgar-mcp

Configuration

  • EDGAR_API_KEY (required): API key for EDGAR Financial API
  • EDGAR_API_URL (optional): defaults to https://www.financialmodelupdater.com
  • EDGAR_MCP_OUTPUT_DIR (optional): path for output="file" responses
    • default: ./exports/file_output from current working directory
    • fallback: ~/.cache/edgar-mcp/file_output

Run

edgar-mcp

Claude Code config snippet:

{
  "mcpServers": {
    "edgar-financials": {
      "type": "stdio",
      "command": "edgar-mcp",
      "env": {
        "EDGAR_API_KEY": "YOUR_KEY_HERE"
      }
    }
  }
}

Requirements

  • Python 3.11+
  • EDGAR API key

See also

  • edgar-parser — The underlying Python library for parsing SEC EDGAR filings. Use this directly if you want to integrate EDGAR data into your own Python application without MCP.

Tools (6)

get_filingsFetch filing metadata including 10-Q, 10-K, and 8-K earnings release references.
get_financialsFetch full period facts as inline JSON or local file output.
get_metricFetch a specific metric or tag for a given period.
list_metricsList candidate metrics or tags available in a filing period.
search_metricsFuzzy-search metrics by natural-language query.
get_filing_sectionsExtract filing narrative sections or tables from 10-K, 10-Q, or 8-K reports.

Environment Variables

EDGAR_API_KEYrequiredAPI key for EDGAR Financial API
EDGAR_API_URLAPI endpoint URL
EDGAR_MCP_OUTPUT_DIRPath for file output responses

Configuration

claude_desktop_config.json
{"mcpServers": {"edgar-financials": {"type": "stdio", "command": "edgar-mcp", "env": {"EDGAR_API_KEY": "YOUR_KEY_HERE"}}}}

Try it

→Find the latest 10-K filing for Apple and extract the risk factors section.
→What are the available financial metrics for Microsoft's most recent 10-Q report?
→Search for metrics related to 'revenue' in the latest filing for NVIDIA.
→Get the total revenue metric for Tesla for the last fiscal year.

Frequently Asked Questions

What are the key features of Edgar MCP?

Fetch filing metadata for 10-K, 10-Q, and 8-K reports. Retrieve full period financial facts. Fuzzy-search for specific financial metrics using natural language. Extract narrative sections and tables from SEC filings. Support for local file output of financial data.

What can I use Edgar MCP for?

Automating financial research by pulling raw data directly from SEC filings into an AI analysis workflow.. Comparing specific financial metrics across multiple quarters for a public company.. Extracting qualitative narrative sections from 10-K reports to summarize business risks or management discussion.. Building custom financial dashboards by programmatically fetching structured data from EDGAR..

How do I install Edgar MCP?

Install Edgar MCP by running: pip install edgar-mcp

What MCP clients work with Edgar MCP?

Edgar MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Edgar MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare
View all ai-tools servers →

Related MCP Servers

Skill Seekers
The data layer for AI systems.
ai-tools11.1K stars
Context Mode
The other half of the context problem.
ai-tools5.6K stars
Semiotic
A React data visualization library designed for AI-assisted development.
ai-tools2.6K stars
RocketRide
Self-hosted, open-source AI pipeline platform for MCP tools
ai-tools1.6K stars
Context+
Semantic Intelligence for Large-Scale Engineering.
ai-tools1.5K stars
ShipSwift
AI-native SwiftUI component library — production-ready code for LLMs
ai-tools1.3K stars