Verix API MCP Server
Enables searching Verix records, retrieving record details, and running analysis workflows through natural language via the Verix API.
README
Verix API MCP Server
A production-ready Model Context Protocol server for the Verix API.
This template lets Claude Desktop, Cursor, Windsurf, and other MCP-compatible clients search Verix records, retrieve record details, and run analysis workflows through controlled Verix API tools.
Built as a starter template for teams that want a secure baseline before adding company-specific Verix API automation, verification workflows, or AI-powered operational tooling.
Who this is for
This repository is useful for:
- developers building AI assistants on top of the Verix API,
- platform teams connecting Verix workflows to Claude, Cursor, or other MCP clients,
- agencies building custom Verix API integrations for clients,
- teams that need a clean TypeScript MCP server example,
- builders creating AI-powered search, record lookup, or analysis workflows.
Features
- TypeScript + Express MCP server
- Streamable HTTP MCP transport
- Verix API client with timeout and retry support
- API key protection for
/mcp - Rate limiting for MCP requests
- Health endpoint at
/health - Structured Pino logging
- Zod-based environment validation
- MCP tools for search, record retrieval, and analysis
- Jest + Supertest test setup
- GitHub Actions CI workflow
Architecture
Claude Desktop / Cursor / Windsurf
│
│ HTTP POST /mcp
│ X-API-Key: <MCP_API_KEY>
▼
Express Server
│
├── Correlation ID middleware
├── Pino HTTP logger
├── Rate limiter
├── MCP API key middleware
│
▼
MCP SDK Handler
│
├── verix_search ─┐
├── verix_get_record ─┤──► Verix REST API
└── verix_analyze ─┘
GET /health → Verix API dependency status
See the larger diagram in docs/architecture.md.
Source Code
The complete production-ready Verix API MCP Server template is available on GitHub.
Repository:
https://github.com/kamolc4/verix-api-mcp-server
The repository includes:
- Complete TypeScript source code
- Verix API client
- MCP tools
- GitHub Actions CI
- Jest test suite
- MIT License
- Claude Desktop & Cursor configuration
- Production deployment examples
Fork the repository or download it as a ZIP to start building immediately.
Available MCP tools
| Tool | Purpose |
|---|---|
verix_search |
Search Verix records using a full-text query with optional filters. |
verix_get_record |
Retrieve a full Verix record by ID, including metadata and timestamps. |
verix_analyze |
Run an analysis job on a Verix record, such as sentiment, classification, extraction, or summary. |
Quick start
1. Install dependencies
# Clone repository
git clone https://github.com/kamolc4/verix-api-mcp-server.git
cd verix-api-mcp-server
# Install dependencies
npm ci
2. Configure environment
cp .env.example .env
Edit .env:
PORT=3000
NODE_ENV=development
LOG_LEVEL=info
MCP_API_KEY=replace-with-a-long-random-secret
VERIX_API_KEY=your-verix-api-key
VERIX_BASE_URL=https://api.verix.example.com/v1
VERIX_TIMEOUT_MS=10000
VERIX_MAX_RETRIES=3
RATE_LIMIT_RPM=60
RATE_LIMIT_WINDOW_MS=60000
3. Run locally
npm run dev
4. Check health
curl http://localhost:3000/health
5. List MCP tools
curl -X POST http://localhost:3000/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H 'X-API-Key: replace-with-your-mcp-api-key' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Verix API configuration
This starter uses API-key based access to the Verix API.
Required environment variables:
| Variable | Description | Required |
|---|---|---|
MCP_API_KEY |
Shared secret required in the X-API-Key header for /mcp. |
Yes |
VERIX_API_KEY |
API key used by this server to call the Verix API. | Yes |
VERIX_BASE_URL |
Base URL for the Verix REST API. | Yes |
VERIX_TIMEOUT_MS |
Timeout for outbound Verix API requests. | No |
VERIX_MAX_RETRIES |
Maximum retry attempts for retryable Verix API failures. | No |
RATE_LIMIT_RPM |
Max requests per rate-limit window. | No |
RATE_LIMIT_WINDOW_MS |
Rate-limit window duration in milliseconds. | No |
The server sends Verix API requests with:
Authorization: Bearer <VERIX_API_KEY>
Connect to Claude Desktop
Build the server first:
npm run build
npm start
Then add an MCP server entry in your Claude Desktop configuration:
{
"mcpServers": {
"verix": {
"url": "http://localhost:3000/mcp",
"headers": {
"X-API-Key": "replace-with-your-mcp-api-key"
}
}
}
}
Restart Claude Desktop after editing the configuration.
Connect to Cursor
In Cursor, add a new MCP server using the HTTP endpoint:
{
"name": "verix",
"url": "http://localhost:3000/mcp",
"headers": {
"X-API-Key": "replace-with-your-mcp-api-key"
}
}
Then restart Cursor or reload the MCP server list.
Security notes
This template is safer than a minimal demo, but you should harden it before production use.
Recommended production changes:
- Store
MCP_API_KEYandVERIX_API_KEYin a managed secret manager. - Rotate API keys regularly.
- Use separate Verix API keys for development, staging, and production.
- Add per-user or per-tenant authorization if multiple users will access the server.
- Add audit logs for every MCP tool call.
- Restrict write-capable tools behind approval workflows before adding them.
- Use HTTPS in production.
- Review Verix API permissions and use the minimum required access.
- Monitor rate limits and API errors.
Security Review
Verify this server with MCPForge:
https://www.mcpforge.tech/verify
MCPForge can help review:
- exposed tools,
- authentication behavior,
- health checks,
- compatibility with MCP clients,
- risk level of record analysis workflows,
- security posture before publishing or deployment.
After verification, you can link your public report from this README:
[](https://www.mcpforge.tech/verified/verix-api-mcp)
Public MCPForge report:
https://www.mcpforge.tech/verified/verix-api-mcp
Starter template on MCPForge Code Hub:
https://www.mcpforge.tech/code/verix-api-mcp-server-starter
Deployment
A common production setup:
- Deploy this service to Railway, Render, Fly.io, AWS, GCP, Azure, or a private Kubernetes cluster.
- Configure environment variables in the hosting provider.
- Set
MCP_API_KEYandVERIX_API_KEYas secrets. - Set
VERIX_BASE_URLto the correct production or sandbox Verix API endpoint. - Verify
/healthbefore connecting production MCP clients. - Verify
/mcpwith a validX-API-Key. - Run a public or private verification with MCPForge.
Local development commands
npm run lint
npm run typecheck
npm test
npm run build
API endpoints
| Method | Path | Description |
|---|---|---|
GET |
/health |
Health and Verix API connectivity check. |
POST |
/mcp |
MCP endpoint protected by X-API-Key. |
Testing
npm test # run all tests
npm run test:watch # watch mode
npm run test:coverage # coverage report
The test suite covers:
/healthsuccess and degraded states,- missing API key on
/mcp, - invalid API key on
/mcp, - valid API key access,
- MCP
tools/list, - successful
verix_search, - Verix API failure handling,
- successful
verix_get_record, - successful
verix_analyze, - rate limit behavior,
- configuration validation.
Releases
Latest stable release:
v1.0.0
See the Releases page for the full changelog.
License
MIT — see LICENSE.
Related MCP Server Templates
Looking for other production-ready MCP Server templates?
- GitHub MCP Server
- Slack MCP Server
- Stripe MCP Server
- Notion MCP Server
- Shopify MCP Server
- HubSpot MCP Server
- PostgreSQL MCP Server
Browse the complete collection:
https://www.mcpforge.tech/code
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。