Skip to main content
Glama
EDGAR SEC Memory MCP

EDGAR SEC Memory MCP

FINSEC — 经认证的 SEC 记忆 MCP 服务器

MCP Registry Glama MCP License Facts Zero Hallucination

Calera Labs FINSEC 的官方 Model Context Protocol(MCP) 连接器。可将 AI 智能体(Claude Desktop、Cursor、Zed、VS Code 以及自定义自主智能体集群)直接连接到由 Calera Episteme-1 Engine 驱动的 4.06M 条经认证的 SEC EDGAR 事实数据。

“前沿模型负责推理——Calera Lattice 提供真值。”


⚡ 核心保证

  • 0.00% 统计幻觉: 事实召回是确定性的并且基于几何计算($A_4$ Pentatope 点阵记忆)。事实检索路径中不存在语言模型。

  • 加密溯源: 返回的每个财务指标都包含精确的 SEC 申报文件 accession 编号、日期、概念和 SHA-256 审计哈希。

  • 诚实拒绝(SAFE_REFUSAL): 如果某项指标没有出现在官方 SEC 申报文件中,或存在歧义,引擎会返回诚实的拒绝结果,而不是虚构数字。

  • 超低延迟与高毛利: 响应序列化时间低于 25 毫秒,支持低 Token 占用模式。


Related MCP server: filingrail-mcp

🚀 一键快速集成

1. Cursor IDE

将以下内容添加到你的项目的 .cursor/mcp.json(或在全局 Cursor 设置 → 功能 → MCP 中):

{
  "mcpServers": {
    "finsec": {
      "url": "https://finsec.caleralabs.com/mcp",
      "headers": {
        "X-License-Key": "clabs_live_YOUR_KEY"
      }
    }
  }
}

(在 dashboard.caleralabs.com 获取你的免费 API 密钥。)


2. Claude Desktop

添加到 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(一键终端命令)

使用Smithery(smithery.ai/servers/calera-labs/finsec)在 Claude 或 Cursor 中自动安装:

# 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 编辑器

添加到 ~/.config/zed/settings.json:

{
  "experimental.context_servers": {
    "finsec": {
      "command": {
        "url": "https://finsec.caleralabs.com/mcp",
        "headers": {
          "X-License-Key": "clabs_live_YOUR_KEY"
        }
      }
    }
  }
}

🛠️ 认证工具集

FINSEC MCP 服务器提供 7 个认证工具:

工具名称

描述

query_financial_sec

对 4.06M 条经认证的 SEC EDGAR 事实执行自然语言查询,返回溯源信息或诚实的 SAFE_REFUSAL。

valuation_inputs

12 个认证估值包(DCF 输入、FCF、Altman Z'、Beneish M、DuPont 5 步法、Piotroski F)。

query_sec_metric_exact

针对公司 + 期间 + 概念的精确单格 EDGAR 指标召回。

compute_sec_cagr

基于经验证的 SEC 申报事实准确计算复合年增长率(CAGR),零虚构。

lattice_arith_evaluate

确定性零错误代数求解器(cagr、ratio、multiply、divide、yoy_series、product_chain)。

vln_capabilities_overview

动态范围概览与能力边界。

query_sec_sector_peers

多公司板块与行业财务比较。


💡 你的智能体示例查询

连接后,直接用自然语言向你的智能体提问即可:

  • “Apple 在 FY2023 的总收入和毛利(美元)是多少?”

  • “比较 Microsoft 和 Alphabet 在 2024 年第三季度的营业利润。”

  • “计算 Nvidia 从 FY2021 到 FY2024 的 3 年营收复合年增长率(CAGR)。”

  • “提取 Tesla 在 2023 年的 DuPont 5 步分析输入。”


🏎️ 针对高 QPS Agent Swarm 的低 Token 模式

为消除高 QPS 多轮推理智能体的上下文耗尽,请在查询中传入 "low_tokens": true,即可实现 71.7% 的 Token 削减:

{
  "id": "q112",
  "st": "OK",
  "val": 383285000000,
  "cur": "USD",
  "concept": "us-gaap:RevenueFromContractWithCustomerExcludingAssessedTax",
  "per": "FY2023",
  "hash": "5ce23625"
}

🔑 身份验证与 API 密钥

在 Universal Dashboard 上生成你的免费或企业级 API 密钥:
👉 https://dashboard.caleralabs.com


🛡️ 安全与溯源策略

  • 事实路径中不使用语言模型: 所有返回的数字均来自经 SEC accession 编号验证的 XBRL/EDGAR 申报表。

  • IP 云边界: 底层算法和 $A_4$ Pentatope 点阵权重在 Calera Labs 安全云运行时中运行。公开客户端仅接收经验证的输出和 schema 响应。


📄 许可与署名

  • 连接器规范和客户端 schema 均根据 Apache-2.0 License 许可。

  • 由 Calera Episteme-1 / Calera Labs 提供支持(Calera Labs 为 Pyrotope Inc. 的对外经营名称,Pyrotope Inc. 是 Calera Computing, Inc. 的子公司)。

Available Tools

7 tools
compute_sec_cagrCompute Certified SEC CAGRA
Read-only
Inspect

Exact compound annual growth rate (CAGR) calculation over verified SEC filing facts. Deterministic mathematical execution with zero language model confabulation.

Inputs: metric (required), company (required), end_period (required), start_period (required), +1 more. Returns: st, per, val, hash, +10 more

lattice_arith_evaluateCertified Financial ArithmeticA
Read-only
Inspect

Deterministic zero-error algebraic solver (cagr, ratio, multiply, divide, yoy_series, product_chain) over verified SEC EDGAR financial metrics.

Inputs: op (required), metric, company, factors, +4 more. Returns: st, per, val, hash, +10 more

query_financial_secQuery Certified SEC FactsA
Read-only
Inspect

Certified SEC fact query. Returns verified values with provenance or SAFE_REFUSAL. Does not invent numbers. Treat SAFE_REFUSAL as success-of-honesty, not a tool failure. Monetary answers default to the filer's reporting currency; request FX conversion via target_currency / usd_only or natural-language 'in USD'.

Inputs: query (required), usd_only, low_tokens, target_currency. Returns: st, per, val, hash, +10 more

query_sec_metric_exactExact SEC Metric RecallA
Read-only
Inspect

Exact EDGAR metric recall for company+metric+period. Server-side verified fact with provenance; SAFE_REFUSAL when missing. No LLM math.

Inputs: metric (required), period (required), company (required), low_tokens. Returns: st, per, val, hash, +10 more

query_sec_sector_peersQuery SEC Sector PeersA
Read-only
Inspect

Returns certified SEC EDGAR XBRL metrics across an industry peer group dynamically derived from SEC filing SIC codes and 10-K business segment disclosures. Use this for sector screening or when no specific company ticker is provided.

Inputs: sector_or_industry (required), limit, period, metrics, +1 more. Returns: st, per, val, hash, +10 more

valuation_inputsGet Certified SEC Valuation PackA
Read-only
Inspect

Certified SEC/EDGAR valuation inputs pack (12 packs including dcf_valuation_inputs historical FCF). Not market EV, P/E, trading DCF, or macro gauges (Buffett Indicator / CAPE).

Inputs: pack (required), company (required), period, low_tokens. Returns: st, per, val, hash, +10 more

vln_capabilities_overviewVLN Capabilities OverviewA
Read-only
Inspect

Returns a complete structured overview of all certified EDGAR valuation packs, deterministic financial arithmetic operations, SEC calculations, and product scope boundaries on finsec.caleralabs.com.

Inputs: low_tokens. Returns: st, per, val, hash, +10 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 7 tools

    Disambiguation2/5

    Several tools overlap heavily: compute_sec_cagr and lattice_arith_evaluate both perform deterministic CAGR/arithmetic over SEC facts, and query_financial_sec and query_sec_metric_exact both return certified SEC metric values with provenance or SAFE_REFUSAL. The detailed descriptions help slightly, but an agent cannot clearly determine which math or query tool to choose.

    Naming Consistency2/5

    Tool names mix patterns: query_* tools are verb-first, but lattice_arith_evaluate is verb-last, and valuation_inputs / vln_capabilities_overview are noun phrases. The unexplained 'vln' abbreviation and inconsistent verb placement make the naming scheme unpredictable.

    Tool Count4/5

    Seven tools is a reasonable size for an SEC/EDGAR valuation server and not excessive. However, the overlapping math and query tools mean the set is slightly inflated rather than each tool occupying a distinct slot.

    Completeness4/5

    Core workflows are covered: certified fact/metric queries, peer screening, valuation input packs, deterministic calculations, and capability discovery. Minor gaps such as missing dedicated company-profile or filing-metadata tools exist but agents can work around them.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Give your AI agent live SEC EDGAR data: company financials, insider trades, 8-K events, 13F holdings, and the raw filings stream — all normalized to clean JSON, every number traceable back to its sec.gov source filing.
      8
      45 PyPI
      MIT