Documentation
Integrations
Pretense is a drop-in proxy. Connect it to any AI coding tool by changing one setting.
Claude Code
RecommendedRoute every Claude Code session through Pretense by setting a single environment variable. All prompts are mutated before reaching the Anthropic API.
- 1Install and start the Pretense proxy (pretense start)
- 2Set ANTHROPIC_BASE_URL in your shell profile or session
- 3Run Claude Code as normal -- mutation happens transparently
# Option 1: per-session ANTHROPIC_BASE_URL=http://localhost:9339 claude "refactor auth.ts" # Option 2: export in ~/.zshrc or ~/.bashrc export ANTHROPIC_BASE_URL=http://localhost:9339
Cursor
Override the model base URL in Cursor settings to route requests through Pretense. Works with GPT-4, Claude, and any OpenAI-compatible model.
- 1Open Cursor and go to Settings (Cmd+,)
- 2Navigate to Models and find "Override OpenAI Base URL"
- 3Set it to http://localhost:9339
- 4Your existing API key works unchanged
# Alternatively, set the env var before launching Cursor OPENAI_BASE_URL=http://localhost:9339 cursor
VS Code Extension
The Pretense VS Code extension adds a status bar indicator, a scan command, and a mutation map viewer. Install from the marketplace.
- 1Search for "Pretense" in the VS Code Extensions panel
- 2Install and reload VS Code
- 3The status bar shows live mutation count and proxy status
- 4Use Cmd+Shift+P and type "Pretense: Scan" to scan the active file
GitHub Copilot
EnterpriseEnterprise Copilot deployments can be routed through Pretense via a proxy configuration in your organization settings. Contact sales for setup assistance.
- 1Requires GitHub Copilot for Business or Enterprise
- 2Configure your organization-level proxy endpoint to http://your-pretense-server:9339
- 3All Copilot requests flow through Pretense before reaching GitHub
- 4Contact hello@pretense.ai for enterprise proxy setup documentation
MCP Server
Claude CodeThe Pretense MCP server registers with Claude Code as a tool. Every prompt is automatically scanned before being sent, with no changes to your workflow.
- 1Install Pretense globally (npm install -g pretense)
- 2Add the MCP server configuration to .claude/settings.json
- 3Reload Claude Code -- the pretense_scan tool is now available
- 4Claude Code automatically calls pretense_scan before sending prompts
// .claude/settings.json
{
"mcpServers": {
"pretense": {
"command": "pretense-mcp",
"args": []
}
}
}CI/CD Pipeline
Block any unprotected LLM API call from reaching production. The Pretense CLI integrates with any CI system that runs Node.js.
- 1Add pretense to your project devDependencies
- 2Run pretense scan ./src as a pre-deploy check
- 3Fail the build if the exit code is non-zero (secrets detected)
- 4Export the scan report as a CI artifact for auditing
# package.json scripts
{
"scripts": {
"scan": "pretense scan ./src --format json --output scan-report.json",
"preflight": "npm run scan && echo 'Scan passed'"
}
}Need a different integration?
If your tool is not listed, email us and we will add official support. Pretense speaks OpenAI-compatible API format so most tools work already.