TehProf Support MCP Server

TehProf Support MCP Server

AI-powered helpdesk management via Model Context Protocol. Connect any MCP-compatible assistant to your support workspace.

Category
访问服务器

README

TehProf Support MCP Server

AI-powered helpdesk management via Model Context Protocol. Connect any MCP-compatible assistant (Claude, ChatGPT, Cursor, Cline) to your support workspace — no custom integration code.

License: MIT MCP Protocol Node Transport: HTTP Tools GitHub stars

TehProf Support (support.tehprof.kz) is a multi-tenant SaaS helpdesk built for IT service companies. This server exposes 36 AI tools covering knowledge search, ticket lifecycle, analytics, automation, and Bitrix24 CRM proxy — gated by subscription tier.

Zero installation: use the hosted endpoint at https://support.tehprof.kz/mcp.

Table of Contents

Quick Start

Option 1 — hosted (recommended)

Add to your MCP client config — no install, no server to run:

{
  "mcpServers": {
    "tehprof-support": {
      "url": "https://support.tehprof.kz/mcp",
      "transport": "streamable-http"
    }
  }
}

For authenticated access (unlocks tier-specific tools):

{
  "mcpServers": {
    "tehprof-support": {
      "url": "https://support.tehprof.kz/mcp",
      "transport": "streamable-http",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Option 2 — sanity check via curl

curl -sX POST https://support.tehprof.kz/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'

You should receive an initialize response with server capabilities.

Tools by Tier

The server gates tools by your TehProf Support plan. Anonymous (no API key) works out of the box.

Free — anonymous, no API key

Tool What it does
knowledge_search Full-text search across the knowledge base
knowledge_read Read a specific article
knowledge_list List articles by category
onboarding_guide Step-by-step setup walkthrough
onboarding_features Feature matrix by plan
demo_create_ticket Create a ticket in the sandbox
demo_view_ticket Inspect a demo ticket
demo_workflow Walk the full ticket lifecycle
pricing_plans List all pricing plans
pricing_calculate Personalized plan recommendation
system_health Platform status probe
system_info Server capabilities
system_tenant_info Your tenant metadata
settings_get Read tenant settings
settings_update Update available settings
settings_operators List operators in your team

Starter

Tool What it does
tickets_list Filtered ticket list
tickets_get Ticket + messages + participants
analytics_dashboard KPI dashboard overview
channels_list Messaging channels
channels_status Per-channel connection state

Pro

Tool What it does
tickets_create Create new tickets; can sync the customer company/contact by your own stable external IDs (idempotent) and dedupe by external_ref
tickets_reply Post replies on behalf of an operator
tickets_update Change status / priority
analytics_sla SLA compliance report
analytics_operators Per-operator performance
automation_rules_list List automation rules
automation_rules_create Create new rules
automation_rules_toggle Enable / disable rules
webhooks_list Outbound webhooks

Business

Tool What it does
bitrix_contacts Search CRM contacts
bitrix_deals List CRM deals
bitrix_tasks Filter Bitrix24 tasks
bitrix_task_create Create Bitrix24 tasks linked to tickets
bitrix_users Portal user directory
channels_configure Configure WA / TG / Email channels

Supported AI Clients

Works with any client that speaks MCP over Streamable HTTP:

  • Claude Desktop — claude_desktop_config.json
  • Claude Code — .mcp.json or ~/.claude/settings.json
  • Cursor — MCP settings panel
  • Cline / Continue.dev — config.json
  • ChatGPT (Custom GPT) — see gpt-config.md
  • Custom agents — any @modelcontextprotocol/sdk consumer

Architecture

┌──────────────────────┐     Streamable HTTP      ┌──────────────────────┐
│  AI Client           │  ──────────────────────▶ │  MCP Server (this)   │
│  (Claude, GPT, ...)  │  JSON-RPC 2.0 + SSE      │  Node 20 + TS strict │
└──────────────────────┘                          └──────────┬───────────┘
                                                             │ HTTP localhost
                                                             ▼
                                                   ┌──────────────────────┐
                                                   │  PHP backend         │
                                                   │  mcp-auth.php        │
                                                   │  mcp-internal.php    │
                                                   └──────────┬───────────┘
                                                              │
                                                              ▼
                                                   ┌──────────────────────┐
                                                   │  SQLite (WAL)        │
                                                   │  Bitrix24 REST       │
                                                   └──────────────────────┘

Why Streamable HTTP (MCP 2025-03-26) and not stdio / SSE? Works through corporate proxies, scales horizontally, no long-lived connections to manage — the canonical transport for remote MCP.

Server Discovery

MCP clients can auto-discover this server via the .well-known endpoint:

GET https://support.tehprof.kz/.well-known/mcp.json

The response lists server capabilities, auth requirements, and tier descriptors.

Authentication

  1. Log in at support.tehprof.kz.
  2. Settings → API Keys → Create.
  3. Use it as Authorization: Bearer <key> in the MCP client header config.
  4. Revoke / rotate any time from the same panel.

Keys are hashed at rest, rate-limited, and validated against the tenant's plan on every call.

The same tenant API key may also be used by GPT/OpenAPI clients against https://support.tehprof.kz/api/openapi.json as Authorization: Bearer <key>. Direct REST integrations that call /api/admin.php use X-Api-Key: <key> instead.

Security

  • Transport: TLS 1.3, HSTS, no mixed content.
  • CORS: allowlist (support.tehprof.kz, claude.ai, chat.openai.com) — no wildcard.
  • Sessions: 1-hour inactivity TTL, evicted every 5 minutes.
  • Tenant isolation: authenticated MCP/OpenAPI calls resolve the tenant from the API key; mismatched tenant_id is rejected with 403.
  • Internal bridge: mcp-auth.php is not public; mcp-internal.php requires Bearer auth for tenant data and write actions require write scope.
  • Secrets: never sent client-side, stored in HashiCorp Vault server-side.
  • Audit log: every tool call is recorded against the tenant.

Report vulnerabilities to ilay25@gmail.com (please do not open public issues for security).

Self-Hosting

For tenants who need the MCP server running in their own network:

git clone https://github.com/tehprof/support-mcp
cd support-mcp
npm install
npm run build
MCP_PORT=8101 MCP_HOST=127.0.0.1 node dist/index.js

Set SUPPORT_BACKEND_URL to point at your Support backend. See CLAUDE.md for full env reference.

FAQ

Does this work without a TehProf account? Yes — anonymous access unlocks 16 free tools (knowledge, onboarding, demo, pricing, system, settings).

Can I use it with ChatGPT? Yes. Use a Custom GPT — configuration is in gpt-config.md.

What if my plan doesn't include a tool? The tool is hidden from tools/list — AI agents never see it. Upgrade at support.tehprof.kz.

How do I list all tools my plan exposes? Call MCP tools/list — the server filters in real time based on your Authorization header.

Where is the source code? Right here — github.com/tehprof/support-mcp. MIT licensed.

Links

Contributing

Pull requests welcome. For non-trivial changes, please open an issue first to discuss.

License

MIT — see LICENSE.

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