bizratings-mcp
Exposes the BizRatings CSAT/NPS customer-survey API for ConnectWise partners as MCP tools.
README
bizratings-mcp
BizRatings MCP server — exposes the BizRatings CSAT/NPS customer-survey API (for ConnectWise partners) as MCP tools.
Overview
This server implements the Model Context Protocol (Streamable HTTP/SSE transport) and wraps the BizRatings API, which manages CSAT/NPS satisfaction surveys tied to ConnectWise tickets and projects. It follows the MSPbots Vendor MCP Service SOP: stateless, no stored credentials, per-request header authentication.
The server itself holds no credentials — the caller obtains a BizRatings OAuth2 access token and passes it per-request through a header.
Quick Start
Docker (recommended)
docker compose up --build
The server starts on http://localhost:8080.
Local (uv)
uv sync
python -m bizratings_mcp
Health Check
curl http://localhost:8080/health
# {"status": "ok", "service": "bizratings-mcp", "transport": "http"}
No token is required for the health endpoint.
授权参数说明 (Authentication)
Every request to /mcp must include a valid BizRatings access token:
X-Bizratings-Token: <access_token>
BizRatings uses OAuth2 Client Credentials (grant_type=client_credentials). The token itself must be obtained by the caller (Agent Platform / upstream gateway) — this server never sees a client_id/client_secret, it only forwards the bearer token to the BizRatings API:
curl -X POST https://bizratingsidp.azurewebsites.net/connect/token \
-H "Content-Type: application/x-www-form-urlencoded" \
-d "grant_type=client_credentials&client_id=<client_id>&client_secret=<client_secret>&scope=BRApi"
Missing or invalid tokens return 401 Unauthorized.
Environment Variables
| Variable | Default | Description |
|---|---|---|
MCP_HTTP_PORT |
8080 |
Listening port |
MCP_HTTP_HOST |
0.0.0.0 |
Listening host |
BIZRATINGS_BASE_URL |
https://api.bizratings.com |
Override if your tenant is routed through a different host |
MCP Endpoint
POST http://localhost:8080/mcp
Connect your MCP client with:
- Transport:
http(Streamable HTTP / SSE) - Header:
X-Bizratings-Token: <access_token>
Tool List
All dates use the DD-Mon-YYYY format (e.g. 15-Mar-2026) unless noted otherwise.
Tickets
| Tool | 功能 | 参数 |
|---|---|---|
bizratings_get_ticket_responses |
查询工单满意度调查结果(分页) | member_name?, filter_by="CompanyName", keyword?, review_type=0, score=0, start_date, end_date, current_page=1, page_size=20 |
bizratings_get_ticket |
按工单号查单条调查结果 | ticket_no (必填, int) |
bizratings_create_ticket |
推送已关闭工单触发满意度调查邮件(写操作,有副作用) | ticket_id, ticket_title, company_rec_id, company_name, contact_rec_id, contact_name, contact_email, ticket_created_on, ticket_closed_on, ticket_updated_on (均必填,均为 ISO 8601), board_name?, resource? |
bizratings_get_ticket_summary |
工单调查汇总统计 | member_name?, filter_by="CompanyName", keyword?, review_type=0, start_date, end_date |
Surveys(项目 / 多站点 / 专项问卷)
| Tool | 功能 | 参数 |
|---|---|---|
bizratings_get_project_responses |
项目类调查结果 | filter_by="CompanyName", keyword?, review_type=0, start_date, end_date, current_page=1, page_size=20 |
bizratings_get_multisite_responses |
跨站点合并工单调查结果 | member_name?, filter_by="CompanyName", keyword?, review_type=0, score=0, start_date, end_date, current_page=1, page_size=20 |
bizratings_get_multisite_employee_rating |
跨站点员工评分 | start_date, end_date, current_page=1, page_size=20 |
bizratings_get_five_question_survey_detail |
5问卷详情 | start_date, end_date, current_page=1, page_size=20 |
bizratings_get_employee_survey_detail |
员工调查详情 | start_date, end_date, current_page=1, page_size=20 |
Stats
| Tool | 功能 | 参数 |
|---|---|---|
bizratings_get_response_summary |
按 view_type 统计 CSAT/NPS 响应数 | start_date, end_date, view_type="Monthly", source="CSAT" |
bizratings_get_client_responses |
按客户维度统计 | filter_by="CompanyName", keyword?, start_date, end_date, current_page=1, page_size=20 |
bizratings_get_employee_responses |
按员工维度统计 | company_name?, start_date, end_date, current_page=1, page_size=20 |
bizratings_get_quarterly_responses |
季度盈利明细统计 | 无参数 |
bizratings_get_quarterly_summary |
季度盈利汇总统计 | 无参数 |
测试示例 (Test Example)
Call bizratings_get_ticket_responses for the last quarter's high scores only:
{
"method": "tools/call",
"params": {
"name": "bizratings_get_ticket_responses",
"arguments": {
"start_date": "01-Jan-2026",
"end_date": "31-Mar-2026",
"current_page": 1,
"page_size": 10
}
}
}
Equivalent curl against the running server (streamable HTTP MCP endpoint):
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "X-Bizratings-Token: <access_token>" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "bizratings_get_ticket_responses",
"arguments": { "start_date": "01-Jan-2026", "end_date": "31-Mar-2026", "page_size": 10 }
}
}'
Expected shape of a successful result (fields abbreviated):
{
"content": [
{
"type": "text",
"text": "{\n \"tickets\": [ { \"ticketID\": 12345, \"companyName\": \"Acme Corp\", \"score\": 9, ... } ],\n \"totalCount\": 42\n}"
}
]
}
API Reference
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.