corpusiq

corpusiq

Cross-source attribution across 37+ business tools. True ROAS in 14 seconds. Not a dashboard. A decision.

Category
访问服务器

README

CorpusIQ Documentation

tokens saved (est.)

CorpusIQ is the live-data brain you plug into Claude or ChatGPT. Connect the tools you already pay for — QuickBooks, Shopify, Klaviyo, Google Ads, GA4, HubSpot, Slack, Gmail, and 35+ more — then ask plain-English questions and get real answers grounded in your own data.


Contents

Getting Started

Everything needed to go from zero to first answer.

Page Description
Quickstart Guide Step-by-step: create account, connect AI, first connector, first prompt
How It Works Architecture, MCP protocol, privacy, rate limits, skills, connectors explained
Examples Claude Desktop config, MCP starter kit
What is CorpusIQ? Product overview and value proposition

Connectors

37+ live-data connectors across 11 categories. Each with setup guides, auth walkthroughs, and example prompts.

Category Connectors
Marketing & Analytics GA4, Google Ads, LinkedIn Ads, Meta Ads, Ahrefs, Semrush, GSC, PostHog, TikTok
Email & Automation Klaviyo, Mailchimp, ActiveCampaign, Constant Contact, Postscript
CRM & Sales HubSpot, LeadConnector, Close, Odoo, Monday.com
Commerce Shopify, Stripe, Amazon Seller, eBay, GunBroker
Finance QuickBooks
Communication Slack, Gmail, Outlook, Calendly, Notion
Files Google Drive, OneDrive, Dropbox, Airtable
Databases PostgreSQL, MSSQL, Cosmos DB, MongoDB

Browse all 37+ connectors →

Prompt Library

Battle-tested prompts for business operators. Copy, paste, get answers.

Page Use Case
Executive Summary Multi-source business health overview
Marketing & ROAS Campaign performance across Google Ads, Meta, LinkedIn
Ecommerce Ops Shopify + Klaviyo + GA4 combined queries
Revenue & Finance QuickBooks P&L, Stripe revenue, overdue invoices
Customer & CRM HubSpot pipeline, lead scoring, deal velocity
Email & SMS Klaviyo campaign performance, list health
Multi-Source Cross-source queries combining 2+ connectors

Browse all 10 prompt templates →

Recipes

Copy-paste workflows for common business operations.

Recipe Connectors Used
Shopify + QuickBooks Reconciliation Shopify, QuickBooks
HubSpot + Klaviyo Pipeline HubSpot, Klaviyo
Weekly Ad ROI Report Google Ads, Meta Ads, GA4
IndexNow Auto-Submit GSC, IndexNow API

Browse all recipes →

How It Works

Understand the platform architecture.

Page Topic
What is CorpusIQ? Product overview
MCP Architecture Model Context Protocol deep dive
Connectors Explained How live-data connectors work
Skills Explained Cross-source runbook system
Metric Specs Canonical KPI definitions and drift detection
Privacy & Security Data handling, encryption, compliance
Rate Limits API quotas and throttling

Browse how-it-works →

Docs

Platform reference for developers and operators.

Page Topic
Architecture System architecture and design decisions
Governance Operational rules, monitoring, safety
Security Auth, encryption, compliance
Reporting Usage stats, token savings, analytics
Search Cross-source search and retrieval
AI Agent Users Using CorpusIQ from autonomous agents
AI Chat Users Using CorpusIQ from Claude/ChatGPT
ChatGPT Integration ChatGPT-specific setup
Supported Agents Compatible AI platforms

Browse docs →

Hermes Community Hub

The largest collection of Hermes resources on GitHub. 39 pages covering architecture, MCP integration, deployment, skills catalog, governance, and production operations. Built from live experience running 24 autonomous agents across 37+ MCP connectors.

Section Content
Architecture Six-layer autonomous agent design
Setup DGX Spark + Mac Mini deployment
Orchestration Hermes, CrewAI, LangGraph, Reflexion
Skills Catalog 133+ skills, single source of truth
MCP Integration 37+ CorpusIQ connectors for agents
Knowledge GBrain, GraphRAG, Dream Cycle, Honcho
Infrastructure DGX, Mac Mini, browser, auth, routing
Governance Rules, crons, monitoring, email ops
Content Ops Video, social, engagement automation
Tools Index 233+ tools with repo links
Troubleshooting Browser, OAuth, cron, model routing

Browse the Hermes Community Hub →

Troubleshooting

Common issues and fixes for CorpusIQ users.

Page Issue
Claude Can't See CorpusIQ MCP connection failures
ChatGPT Can't See CorpusIQ ChatGPT integration issues
Connector Auth Failed OAuth and credential problems
Connector Shows No Data Empty results, permission gaps
Error Codes Reference All error codes and resolutions

Browse troubleshooting →

Community & Contributing

Page Content
Contributing Specific enhancement requests, recipes, examples, and bug reports
Community Questions, early ideas, upvotes, and discussion paths
Progress Documentation completion tracker
Changelog What changed and when
Roadmap Upcoming features and docs

Quick Reference

Question Answer
How do I get started? Quickstart →
What connectors are available? All 37+ connectors →
How do I write a good prompt? Prompt library →
How does it work under the hood? How It Works →
Can my autonomous agent use this? Hermes Community Hub →
Something's broken. Help? Troubleshooting →
I want to contribute. Contributing →
I have a connector idea. Community →

Repo Stats

Metric Value
Total pages 130+
Connector docs 37+
Prompt templates 10
Recipes 5
Troubleshooting guides 6
Hermes hub pages 39
Hermes tools indexed 140+
Total lines 10,000+

Topics

mcp model-context-protocol ai-connectors business-intelligence claude chatgpt shopify quickbooks google-analytics hubspot stripe ai-agents llm-tools saas hermes

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选