infoset-mcp

infoset-mcp

MCP server for Infoset CRM that enables AI assistants to manage tickets, contacts, companies, SLA, and email threads with built-in rate limit handling and batch operations.

Category
访问服务器

README

<div align="center">

<img src="https://img.shields.io/badge/MCP-Infoset%20CRM-0066FF?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJ3aGl0ZSI+PHBhdGggZD0iTTIwIDJINGMtMS4xIDAtMi45LTIgLjktMkgxMHYyaDRWMmg2YzEuMSAwIDIgLjkgMiAydjE4YzAgMS4xLS45IDItMiAySDRjLTEuMSAwLTItLjktMi0yVjRjMC0xLjEuOS0yIDItMmgxNnptMCAySDR2MTZoMTZWNHpNNiA4aDEydjJINnptMCA0aDEydjJINnptMCA0aDh2Mkg2eiIvPjwvc3ZnPg==&logoColor=white" alt="Infoset MCP" />

infoset-mcp

Model Context Protocol server for Infoset CRM helpdesk and ticket management

Tickets · Contacts · Companies · SLA · Email Threads · Batch Operations

CI Release GitHub release License: MIT Node.js MCP

</div>


Why infoset-mcp?

AI assistants need structured access to helpdesk data. REST APIs require authentication boilerplate, pagination handling, and rate limit management on every call. infoset-mcp wraps the Infoset CRM API into 16 MCP tools with built-in retry logic, rate limit protection, and batch operations, so your AI assistant can query tickets, contacts, and companies without dealing with HTTP plumbing.

  • API key auth: stateless X-API-Key header, no token refresh, no login flow
  • Rate limit aware: monitors x-ratelimit-remaining headers, auto-pauses before hitting limits
  • Retry with backoff: automatic 429 retry (3 attempts, 60s intervals)
  • Batch tools: fetch multiple tickets, logs, contacts, or companies in a single call with controlled concurrency
  • 3 dependencies: @modelcontextprotocol/sdk, axios, zod

Quick Start

git clone https://github.com/sudohakan/infoset-mcp.git
cd infoset-mcp
npm install

MCP Client Configuration (Recommended)

Using env-wrapper (reads credentials from .env, no secrets in config):

{
  "mcpServers": {
    "infoset": {
      "command": "/absolute/path/to/infoset-mcp/scripts/env-wrapper.sh",
      "args": ["/absolute/path/to/infoset-mcp/src/mcp-server.mjs"],
      "env": {}
    }
  }
}

Then create a .env file:

cp .env.example .env
# Set INFOSET_API_KEY in .env

Environment Variables

Variable Required Default Description
INFOSET_API_KEY Yes - Infoset API key (sent as X-API-Key header)
INFOSET_BASE_URL No https://api.infoset.app API base URL
INFOSET_USER_ID No Auto-detected Override user ID for owner-based filtering

Tools

Ticket Operations (7 tools)

Tool Description
infoset_list_tickets List tickets with status, owner, date, sort filters and pagination
infoset_get_ticket Get full ticket detail by ID
infoset_search_tickets Search tickets by keyword with status and priority filters
infoset_create_ticket Create a new ticket with subject, contact, priority, content
infoset_update_ticket Update ticket status, priority, owners, subject, stage, pipeline
infoset_get_ticket_logs Get activity logs for a ticket
infoset_get_ticket_stats Get ticket count breakdown by status (Open/Pending/Resolved/Closed)

Contact and Company (3 tools)

Tool Description
infoset_get_contact Get contact details by ID
infoset_list_contacts List or search contacts by name, email, phone
infoset_get_company Get company details by ID

Communication and SLA (2 tools)

Tool Description
infoset_get_email Get email thread content by email ID
infoset_get_sla_breaches Get SLA breach data for a ticket

Batch Operations (4 tools)

Tool Description
infoset_batch_get_tickets Get multiple tickets in parallel (concurrency: 5)
infoset_batch_get_ticket_logs Get logs for multiple tickets in parallel
infoset_batch_get_contacts Get multiple contacts with auto-deduplication
infoset_batch_get_companies Get multiple companies with auto-deduplication

Reference Codes

1 2 3 4
Status Open Pending Resolved Closed
Priority Low Normal High Urgent

Architecture

MCP Client (Claude, Cursor)  <--stdio-->  infoset-mcp (Node.js)  <--HTTPS-->  Infoset API
                                               |
                                    API Key Auth (X-API-Key)
                                    Rate Limit Monitor
                                    Retry Handler (429)
  • Transport: stdio (spawned by MCP client, JSON over stdin/stdout, logs to stderr)
  • Auth: X-API-Key header on every request, no token management needed
  • Rate limiting: monitors x-ratelimit-remaining, pauses 60s when remaining < 2
  • Retry: 429 responses trigger up to 3 retries with 60s backoff
  • Batch concurrency: max 5 parallel API calls per batch operation

Development

npm test              # Run 29 tests
npm run test:coverage # Run with coverage report
npm start             # Start server standalone

Contributing

See CONTRIBUTING.md for development setup, code style, and pull request guidelines.

Security

See SECURITY.md for credential handling and vulnerability reporting.


<div align="center">

MIT | Built with Claude Code

</div>

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