Dingdawg Finance Agent

io.github.dingdawg由 GitHub 账号 dingdawg 发布v2.0.7更新于 Oct 26, 2026

Financial analysis AI. Forecasting, audit prep, SOX/GAAP compliance. Accuracy compounds with use.

发布方自己的服务：Finance Foundation

已验证STDIO仅桌面金融数据与分析

服务详情

标识符: io.github.dingdawg/dingdawg-finance-agent
传输: STDIO
运行时: Desktop only
信任: Verified
发布于: Sep 16, 2026

安全提示

MCP 服务会接收对话中的工具调用请求，并可能执行外部操作。启用前请先了解该服务能做什么，并只授予它所需的权限。

注册中心已验证此条目所属的 GitHub 账号 dingdawg。这并不表明该账号就是产品方。

SourceWeft 的检查只涵盖条目是否完整、端点是否响应；不审查服务器的代码，也不审查其工具的行为。

在 README 中添加徽章

向读者展示该 MCP 服务已收录于 SourceWeft，徽章链接到本页。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.dingdawg%2Fdingdawg-finance-agent.svg)](https://sourceweft.com/mcp/io.github.dingdawg%2Fdingdawg-finance-agent?utm_source=readme&utm_medium=badge)

概览

AI 生成的概览

本地 MCP 服务器，为助手提供财务比率分析、预算预测、SOX/GAAP 合规检查、费用分类和风险评估工具。

可以做什么: 执行流动性、盈利能力和偿债能力等财务比率分析，并对照行业基准
生成预算预测和多情景建模
检查 SOX/GAAP 合规情况并指出控制缺口
对费用进行分类并识别异常
评估风险敞口，付费版提供蒙特卡洛模拟
每次调用返回结构化 JSON 并附带治理回执
适用场景: 适合助手需要处理财务报表、预算、合规审查或费用数据，并输出结构化、可审计结果的场景。免费版仅覆盖基础比率分析和有限的每日调用次数，更深入的建模与合规分析需要付费密钥。
运行要求: 通过 npx 在本地运行，需要 Node.js。付费功能需要 DINGDAWG_API_KEY 环境变量，免费密钥可向厂商申请。付费的 LLM 功能需要网络访问。

安装前请注意

服务器要求提供 API 密钥（DINGDAWG_API_KEY），付费版需付费：Pro 每月 49 美元或每次调用 0.25 美元，免费版有每日调用上限。付费版提交的财务数据会由厂商服务处理。输出仅为分析辅助，不构成专业财务或审计意见。

安装

在 SourceWeft 中

打开控制台中的 Dingdawg Finance Agent，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照仓库中的启动说明。

README

dingdawg-finance-agent

Breakthrough financial analysis bottlenecks. AI finance that learns YOUR business metrics.

AI-powered financial analysis, budget forecasting, compliance checking, expense categorization, and risk assessment. Free tier runs ratio analysis locally. Paid tier provides LLM-powered financial modeling with SOX and GAAP compliance tracking. Every action is governed and receipted.

For AI Assistants

This MCP server returns structured JSON for seamless integration:

Financial ratios (liquidity, profitability, solvency) with industry benchmarks
SOX/GAAP compliance status with specific control gap identification
Governance receipt on every call (audit-ready)
Chain-ready: financial_analysis for baseline -> budget_forecast for projections -> compliance_check for SOX/GAAP -> expense_categorize for line items -> risk_assessment for exposure

Composable with any MCP client: Claude Code, Cursor, VS Code, ChatGPT Desktop, Windsurf.

Install

Claude Code

Cursor

Add to .cursor/mcp.json:

json

{"mcpServers": {"finance": {"command": "npx", "args": ["dingdawg-finance-agent"], "env": {"DINGDAWG_API_KEY": "your-key"}}}}

{"mcpServers": {"finance": {"command": "npx", "args": ["dingdawg-finance-agent"], "env": {"DINGDAWG_API_KEY": "your-key"}}}}

Full Stack (all 13 agents)

Tools

Tool	Free Tier	Paid Tier
`financial_analysis`	10/day, basic ratio analysis	Unlimited, LLM-powered with industry benchmarking
`budget_forecast`	5/day, linear projection	Unlimited, AI-powered multi-scenario modeling
`compliance_check`	5/day, checklist-based SOX/GAAP	Unlimited, deep compliance with control gap analysis
`expense_categorize`	20/day, rule-based categorization	Unlimited, AI-powered with anomaly detection
`risk_assessment`	5/day, basic risk scoring	Unlimited, Monte Carlo simulation with risk factors

Pricing

Free: 10 analyses/day, basic ratios
Pro: $49/mo, 100 calls/day, AI-powered deep analysis
Pay-as-you-go: $0.25/call, no commitment

Get API key: https://dingdawg.com/developers

Governed

Every call is receipted and auditable. Financial analyses reference GAAP standards and SOX control requirements. Budget forecasts include methodology disclosure. Risk assessments include confidence intervals and assumption documentation.