finsec-mcp
Connects AI agents to over 4 million certified SEC EDGAR financial facts with cryptographic provenance and zero hallucination.
README
FINSEC — Certified SEC Memory MCP Server
Official Model Context Protocol (MCP) connector for Calera Labs FINSEC. Connects AI agents (Claude Desktop, Cursor, Zed, VS Code, and custom autonomous swarms) directly to 4.06M certified SEC EDGAR facts powered by the Calera Episteme-1 Engine.
"Frontier Models Reason — The Calera Lattice Supplies Ground Truth."
⚡ Key Guarantees
- 0.00% Statistical Hallucination: Fact recall is deterministic and geometric ($A_4$ Pentatope lattice memory). No language model exists in the fact retrieval path.
- Cryptographic Provenance: Every returned financial metric includes exact SEC filing accessions, dates, concepts, and SHA-256 audit hashes.
- Honest Refusal (
SAFE_REFUSAL): If a metric is not present in official SEC filings or is ambiguous, the engine returns an honest safe refusal rather than confabulating numbers. - Ultra-Low Latency & High Gross Margins: Sub-25ms response serialization with low token footprint mode.
🚀 1-Click Quickstart Integrations
1. Cursor IDE
Add the following to your project's .cursor/mcp.json (or global Cursor Settings → Features → MCP):
{
"mcpServers": {
"finsec": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
(Get your free API key at dashboard.caleralabs.com)
2. Claude Desktop
Add to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"finsec": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
3. Smithery CLI (1-Click Terminal Command)
Install automatically across Claude or Cursor using Smithery (smithery.ai/servers/calera-labs/finsec):
# For Claude Desktop
npx -y @smithery/cli install financesec-mcp --client claude
# For Cursor
npx -y @smithery/cli install financesec-mcp --client cursor
4. Zed Editor
Add to ~/.config/zed/settings.json:
{
"experimental.context_servers": {
"finsec": {
"command": {
"url": "https://finsec.caleralabs.com/mcp",
"headers": {
"X-License-Key": "clabs_live_YOUR_KEY"
}
}
}
}
}
🛠️ Certified Tools Surface Area
The FINSEC MCP server exposes 7 certified tools:
| Tool Name | Description |
|---|---|
query_financial_sec |
Natural-language query over 4.06M certified SEC EDGAR facts with provenance or honest SAFE_REFUSAL. |
valuation_inputs |
12 Certified Valuation Packs (DCF inputs, FCF, Altman Z', Beneish M, DuPont 5-step, Piotroski F). |
query_sec_metric_exact |
Exact single-cell EDGAR metric recall for company + period + concept. |
compute_sec_cagr |
Exact compound annual growth rate (CAGR) calculation over verified SEC filing facts with zero confabulation. |
lattice_arith_evaluate |
Deterministic zero-error algebraic solver (cagr, ratio, multiply, divide, yoy_series, product_chain). |
vln_capabilities_overview |
Dynamic scope overview and capability boundaries. |
query_sec_sector_peers |
Multi-company sector & industry financial comparisons. |
💡 Example Queries for Your Agent
Once connected, simply ask your agent in plain English:
- "What was Apple's FY2023 total revenue and gross margin in USD?"
- "Compare Microsoft and Alphabet Q3 2024 operating income."
- "Calculate Nvidia's 3-year revenue CAGR from FY2021 to FY2024."
- "Pull the DuPont 5-step analysis inputs for Tesla in 2023."
🏎️ Low-Token Mode for High-QPS Agent Swarms
To eliminate context exhaustion in multi-turn reasoning agents, pass "low_tokens": true in your queries for a 71.7% token reduction:
{
"id": "q112",
"st": "OK",
"val": 383285000000,
"cur": "USD",
"concept": "us-gaap:RevenueFromContractWithCustomerExcludingAssessedTax",
"per": "FY2023",
"hash": "5ce23625"
}
🔑 Authentication & API Keys
Generate your free or enterprise API key on the Universal Dashboard:
👉 https://dashboard.caleralabs.com
🛡️ Security & Provenance Policy
- No Language Model in the Fact Path: All returned numbers originate from XBRL/EDGAR filing tables verified against SEC accessions.
- IP Cloud Boundary: Substrate algorithms and $A_4$ Pentatope lattice weights operate inside Calera Labs secure cloud runtimes. Public clients receive only verified outputs and schema responses.
📄 License & Attribution
- Connector specification and client schemas are licensed under the Apache-2.0 License.
- Powered by Calera Episteme-1 / Calera Labs (DBA of Pyrotope Inc., Subsidiary of Calera Computing, Inc.).
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。