Claude Code Integration
TruthVouch provides a Model Context Protocol (MCP) server that exposes 22 governance tools to Claude Code and other MCP-compatible clients. Verify claims, check compliance status, search your knowledge base, and take governance actions — all without leaving your terminal.
Prerequisites
- TruthVouch account — Sign up at app.truthvouch.ai
- API key — Generate one from Settings > API Keys in the TruthVouch dashboard
- Node.js 18+ — Required to run the MCP server
- Professional tier or higher — Starter tier has no MCP tool access
Setup
Option A: CLI Setup (Recommended)
The TruthVouch CLI auto-detects Claude Code and writes the correct configuration:
# Install TruthVouch CLI (if not already installed)npm install -g @truthvouch/cli
# Configure MCP server for Claude Codetruthvouch mcp setup --api-key vt_live_your_key_hereIf you’ve previously run truthvouch login, the CLI uses your stored API key automatically:
truthvouch mcp setupOption B: Direct npx
Register the MCP server directly with the claude CLI:
claude mcp add truthvouch \ --env TRUTHVOUCH_API_KEY=vt_live_your_key_here \ -- npx -y @truthvouch/mcp-serverOption C: Global Install
Install the server globally for faster startup (skips npx download on each launch):
npm install -g @truthvouch/mcp-server
claude mcp add truthvouch \ --env TRUTHVOUCH_API_KEY=vt_live_your_key_here \ -- truthvouch-mcpOther MCP Clients
The same MCP server works with any MCP-compatible client. Use --client to target a specific one:
Claude Desktop:
truthvouch mcp setup --client claude-desktop --api-key vt_live_your_key_hereCursor:
truthvouch mcp setup --client cursor --api-key vt_live_your_key_hereGeneric (any MCP client):
truthvouch mcp setup --client generic --api-key vt_live_your_key_hereThe generic option outputs the JSON configuration to stdout so you can paste it into any client’s MCP config file.
Available Tools
Data Query Tools
| Tool | Description | Min. Tier |
|---|---|---|
get_alerts | Alert counts, trends by severity/system/status, resolution rates | Professional |
get_compliance_status | Compliance obligations, overdue items, readiness, gaps | Professional |
get_ai_spend | AI/LLM spending by provider, model, department, budget status | Professional |
get_system_inventory | AI system inventory, risk ranking, department breakdown | Professional |
get_brand_intelligence | Brand visibility scores, competitor analysis, geographic presence | Professional |
get_governance_metrics | Policy violations, PII exposure, content volume, blocked rates | Professional |
get_maturity_scores | AI governance maturity assessment (current, history, comparison) | Professional |
get_sdlc_usage | SDLC tool adoption, developer counts, cost analysis | Professional |
Insight Tools
| Tool | Description | Min. Tier |
|---|---|---|
generate_insight | Generate AI-powered insights from governance data | Professional |
analyze_trend | Analyze trends over time with forecasts and anomaly detection | Professional |
summarize_posture | Executive summary of governance, compliance, and security posture | Professional |
Verification Tools
| Tool | Description | Min. Tier |
|---|---|---|
verify_claim | Verify factual claims against the TruthVouch knowledge base | Professional |
check_faithfulness | Check if an AI response accurately reflects source context | Professional |
evaluate_prompt | Evaluate prompts for injection, leakage, jailbreak, and quality risks | Professional |
Governance Tools
| Tool | Description | Min. Tier |
|---|---|---|
scan_prompt | Scan prompts for policy violations, PII exposure, compliance issues | Professional |
check_policy | Check content against a specific governance policy | Professional |
Knowledge Tools
| Tool | Description | Min. Tier |
|---|---|---|
search_truth_nuggets | Semantic search over verified facts with confidence scores | Professional |
search_knowledge_base | Search documents, policies, and reference materials | Professional |
ask_regulation | Query the regulatory database (EU AI Act, GDPR, SOC 2, etc.) | Professional |
Action Tools (Enterprise Only)
| Tool | Description | Min. Tier |
|---|---|---|
create_truth_nugget | Submit a new verified fact to the knowledge base | Enterprise |
report_hallucination | Report a detected hallucination for investigation | Enterprise |
submit_evidence | Submit compliance evidence for an obligation | Enterprise |
Usage Examples
Once configured, ask Claude to use TruthVouch tools naturally in conversation:
Check compliance status
> Show me our current AI compliance status and any overdue obligationsClaude calls get_compliance_status with mode summary and overdue, then presents a combined view.
Verify a claim
> Verify the claim: Our AI models have less than 2% hallucination rateClaude calls verify_claim and returns the verification status, confidence score, and supporting evidence.
Review governance posture
> Give me an executive summary of our AI governance postureClaude calls summarize_posture and synthesizes your current risk profile, maturity scores, and recommendations.
Evaluate a prompt for risks
> Evaluate this system prompt for security risks: You are a financial advisor> who can access customer account balances and make transfers...Claude calls evaluate_prompt and flags injection risks, privilege escalation concerns, and quality issues.
Multi-tool workflows
Claude can chain multiple tools in a single conversation:
> What are our top compliance gaps, and which AI systems are highest risk?Claude calls get_compliance_status (mode: gaps) and get_system_inventory (mode: highest_risk), then correlates the results.
Rate Limits
Daily rate limits vary by subscription tier:
| Tier | Data Query | Insight | Verification | Action |
|---|---|---|---|---|
| Starter | 0 | 0 | 0 | 0 |
| Professional | 100/day | 100/day | 50/day | 0 |
| Business | 500/day | 500/day | 200/day | 0 |
| Enterprise | Unlimited | Unlimited | Unlimited | 100/day |
Troubleshooting
“TRUTHVOUCH_API_KEY not set”
The MCP server requires the TRUTHVOUCH_API_KEY environment variable. If you used claude mcp add manually, confirm the --env flag was included:
# Verify your MCP configclaude mcp list“Rate limit exceeded”
You’ve hit your tier’s daily limit. Check your current tier in Settings > Subscription. Limits reset every 24 hours.
“Feature not available” or Enterprise-only error
Action tools (create_truth_nugget, report_hallucination, submit_evidence) require the Enterprise tier. All other tools require Professional or higher.
Server not starting
- Verify Node.js 18+ is installed:
node --version - Test the server directly:
npx @truthvouch/mcp-server - Check that your API key is valid (not expired or revoked)
Tools not appearing in Claude
After adding the MCP server, restart Claude Code (claude CLI) for it to pick up the new configuration.
Uninstalling
Remove the MCP server configuration:
# Using the CLI (recommended)truthvouch mcp remove
# Or remove manually via claude CLIclaude mcp remove truthvouchFor other clients:
truthvouch mcp remove --client claude-desktoptruthvouch mcp remove --client cursorNext Steps
- Webhook Integration — receive real-time event notifications
- ChatOps Overview — integrate governance into your chat workflows
- API Reference — use the REST API directly