SEC EDGAR Agent Kit
A multi-framework monorepo toolkit for building AI agents and applications that can access and analyze SEC EDGAR filing data. Built on top of the sec-edgar-mcp Model Context Protocol server.
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A multi-framework monorepo toolkit for building AI agents and applications that can access and analyze SEC EDGAR filing data. Built on top of the sec-edgar-mcp Model Context Protocol server.
AI agent toolkit for accessing and analyzing SEC EDGAR filing data. Build intelligent agents with LangChain, MCP-use, Gradio, Dify, and smolagents to analyze financial statements, insider trading, and company filings.
This monorepo contains multiple packages and integrations, each optimized for different AI agent frameworks and use cases.
This monorepo is organized using modern tooling and contains multiple packages. You can install individual packages from npm:
# LangChain toolkit
npm install @sec-edgar-agentkit/langchain
# MCP-use natural language interface
npm install @sec-edgar-agentkit/mcp-use
# smolagents Python package
pip install sec-edgar-agentkit-smolagents
For Gradio and Dify setup instructions, see their respective documentation:
# Clone the repository
git clone https://github.com/stefanoamorelli/sec-edgar-agentkit
cd sec-edgar-agentkit
# Install all dependencies (monorepo)
bun install
# Build all packages
bun run build
Prerequisites:
import { SECEdgarAgentToolkit } from './integrations/langchain';
const toolkit = new SECEdgarAgentToolkit({
mcpServerUrl: 'sec-edgar-mcp',
configuration: {
actions: {
companies: { lookupCIK: true, getInfo: true },
filings: { search: true, getContent: true },
}
}
});
const tools = toolkit.getTools();
// Use with any LangChain agent
import { agent, analyzeFinancials } from './integrations/mcp-use';
// Simple function calls
const appleInfo = await agent.use("Look up Apple's latest 10-K filing");
const analysis = await analyzeFinancials('AAPL', 3);
# Run the Gradio interface
cd integrations/gradio
./run.sh
# Access at http://localhost:7860
# Or manually:
pip install -r requirements.txt
python app.py
{
actions: {
companies: {
lookupCIK: boolean, // CIK lookup by name/ticker
getInfo: boolean, // Company information
getFacts: boolean, // XBRL company facts
},
filings: {
search: boolean, // Search filings
getContent: boolean, // Extract filing content
analyze8K: boolean, // Analyze 8-K reports
extractSection: boolean, // Extract specific sections
},
financial: {
getStatements: boolean, // Financial statements
parseXBRL: boolean, // XBRL data parsing
},
insiderTrading: {
analyzeTransactions: boolean, // Forms 3/4/5 analysis
}
}
}
sec_edgar_cik_lookup: Look up a company's CIK by name or tickersec_edgar_company_info: Get detailed company informationsec_edgar_company_facts: Retrieve XBRL company factssec_edgar_filing_search: Search for filings with filterssec_edgar_filing_content: Extract filing contentsec_edgar_analyze_8k: Analyze 8-K reportssec_edgar_financial_statements: Extract financial statementssec_edgar_xbrl_parse: Parse XBRL data for precise valuessec_edgar_insider_trading: Analyze insider transactionsconst result = await executor.invoke({
input: "Find Microsoft's CIK and get their latest 10-K filing summary"
});
const result = await executor.invoke({
input: "Compare Apple's revenue growth over the last 3 years using their 10-K filings"
});
const result = await executor.invoke({
input: "Show me insider selling activity for Tesla in the last quarter"
});
import { SECEdgarAgentToolkit } from './integrations/langchain';
import { ChatOpenAI } from '@langchain/openai';
import { AgentExecutor, createStructuredChatAgent } from 'langchain/agents';
const toolkit = new SECEdgarAgentToolkit({
mcpServerUrl: 'sec-edgar-mcp',
configuration: {
actions: {
companies: { lookupCIK: true, getInfo: true },
filings: { search: true, analyze8K: true },
financial: { getStatements: true, parseXBRL: true },
}
}
});
const agent = await createStructuredChatAgent({
llm: new ChatOpenAI({ modelName: 'gpt-4' }),
tools: toolkit.getTools(),
prompt: ChatPromptTemplate.fromMessages([
['system', 'You are a financial analyst with access to SEC EDGAR data.'],
['human', '{input}'],
['assistant', '{agent_scratchpad}']
])
});
const executor = new AgentExecutor({ agent, tools: toolkit.getTools() });
const result = await executor.invoke({
input: "Compare Apple and Microsoft's revenue growth over the last 3 years"
});
import { agent } from './mcp-use';
// Natural language queries
const result = await agent.use(`
Find Tesla's latest 8-K filing and summarize any material events.
Also show me their insider trading activity for the past month.
`);
console.log(result);
Contributions are welcome! Please feel free to submit a Pull Request.
© 2025 Stefano Amorelli
This open-source project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). This means:
For commercial licensing options or other licensing inquiries, please contact [email protected].
Author: Stefano Amorelli
AI agent toolkit for accessing and analyzing SEC EDGAR filing data. Build intelligent agents with LangChain, MCP-use, Gradio, Dify, and smolagents to analyze financial statements, insider trading, and
總覽
AI agent toolkit for accessing and analyzing SEC EDGAR filing data. Build intelligent agents with LangChain, MCP-use, Gradio, Dify, and smolagents to analyze financial statements, insider trading, and company filings.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Sec Edgar Agentkit 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 AI agent toolkit for accessing and analyzing SEC EDGAR filing data. Build intelligent agents with LangChain, MCP-use, Gradio, Dify, and smolagents to analyze financial statements, insider trading, and company filings.