,APEX MCP Server
# APEX MCP Server
Model Context Protocol (MCP) server for APEX - Regulatory intelligence platform for European enterprises.
## Installation
### From npm (recommended)
```bash
npm install -g @apex-dev/mcp-server
```
### From source
```bash
git clone https://github.com/apex-dev/mcp-server.git
cd mcp-server
npm install
npm run build
```
## Configuration
Add to your MCP configuration file:
**Claude Desktop** (`~/Library/Application Support/Claude/claude_desktop_config.json`):
```json
{
"mcpServers": {
"apex": {
"command": "npx",
"args": ["-y", "@apex-dev/mcp-server"],
"env": {
"APEX_API_KEY": "your_api_key_here",
"APEX_API_BASE": "https://api.apex.dev"
}
}
}
}
```
**Cursor** (`~/.cursor/mcp.json`):
```json
{
"mcpServers": {
"apex": {
"command": "npx",
"args": ["-y", "@apex-dev/mcp-server"],
"env": {
"APEX_API_KEY": "your_api_key_here"
}
}
}
}
```
**Cline** (VS Code extension - configure in settings):
```json
{
"mcpServers": {
"apex": {
"command": "npx",
"args": ["-y", "@apex-dev/mcp-server"],
"env": {
"APEX_API_KEY": "your_api_key_here"
}
}
}
}
```
## Available Tools
### `apex_search`
Search regulatory publications from European sources (RGPD, ISO27001, AI Act, etc.)
**Parameters:**
- `query` (string): Search terms
- `topics` (array): Topic IDs to filter
- `from` (string): Start date (ISO 8601)
- `to` (string): End date (ISO 8601)
- `limit` (number): Max results
**Example:** "Search for GDPR and AI regulations from the last 30 days"
### `apex_create_topic`
Create a new monitoring topic.
**Parameters:**
- `name` (string): Topic name
- `keywords` (array): Keywords to monitor
**Example:** "Create a topic called AI_REGULATION with keywords: artificial intelligence, machine learning, AI Act"
### `apex_list_topics`
List all available monitoring topics.
### `apex_create_follow`
Set up monitoring with notifications.
**Parameters:**
- `topics` (array): Topic IDs to follow
- `frequency` (string): "realtime", "daily", or "weekly"
- `channels` (array): ["email", "slack", "webhook"]
### `apex_generate_brief`
Generate a compliance brief.
**Parameters:**
- `period` (string): "daily", "weekly", or "custom"
- `topics` (array): Topic IDs to include
- `format` (string): "markdown", "json", or "html"
## Use Cases
### For European TPE/PME
- Monitor RGPD compliance updates
- Track ISO27001 certification requirements
- Stay updated on AI Act implementation
### For Developers
- Get regulatory context when building compliance-aware applications
- Automate compliance monitoring in CI/CD pipelines
- Generate regulatory briefs for stakeholders
### For AI Agents
- Access real-time regulatory intelligence
- Create compliance monitoring workflows
- Generate structured compliance reports
## API Integration
For direct API integration (without MCP), see: https://docs.apex.dev
## Development
```bash
# Install dependencies
npm install
# Build
npm run build
# Run in development
npm run dev
# Test with MCP inspector
npx @modelcontextprotocol/inspector node dist/index.js
```
## License
MIT © 2026 APEX
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: apex_create_follow handles notification setups, apex_create_topic manages topic creation, apex_generate_brief produces summaries, apex_list_topics retrieves topic lists, and apex_search performs regulatory searches. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent 'apex_verb_noun' pattern with snake_case, such as apex_create_follow and apex_list_topics. This uniformity enhances readability and predictability across the toolset, with no deviations in naming conventions.
With 5 tools, the server is well-scoped for regulatory monitoring and compliance intelligence. Each tool serves a specific function (creation, listing, searching, briefing) without redundancy, making the count appropriate and manageable for the domain.
The toolset covers key operations like creating and listing topics, generating briefs, and searching publications, which supports core workflows. A minor gap exists in update or delete functionality for topics or follows, but agents can likely work around this for basic monitoring tasks.