White Pact MCP Server

WhitePact - an independent runtime authority, governance, and assurance layer for autonomous systems: a five-way governance decision engine (ALLOW / ALLOW_WITH_REDACTION / REQUIRE_APPROVAL / DENY / QUARANTINE), trust scoring, bias detection, guardrails, hallucination detection, compliance mapping (NIST AI RMF / EU AI Act / ISO 42001), cost intelligence, drift monitoring, a public Trust Index / leaderboard / AI…. Its 27 documented tools cover rai, scan, trust, redteam.

People who work with rai, scan and trust and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-30 · ★ 2 · #75 OF 216 MAINTAINED SECURITY · VERIFIED 2026-09-30

MIT · Python servers · how we verify → /methodology

01 · Install White Pact

before you install - you'll need

Set RAI_API_URL, RAI_API_KEY, RAI_DB_PATH, RAI_API_KEYS, RAI_AUTH_ENABLED, RAI_DB_URL, RAI_DATABASE_URL, RAI_REDIS_URL, RAI_OTEL_ENDPOINT before connecting.

Claude Code

claude mcp add guruprasath-annadurai-whitepact --transport http https://whitepact-mcp-http.onrender.com/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "guruprasath-annadurai-whitepact": {
      "url": "https://whitepact-mcp-http.onrender.com/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://whitepact-mcp-http.onrender.com/mcp

transport: streamable-http

endpoint NOT responding · probed 2026-09-30

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · remote - your agent's requests go to whitepact-mcp-http.onrender.com

license MIT - declared in the repository

pypi package rai-governance-platform - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.Guruprasath-Annadurai is GitHub-verified and matches the repo owner

03 · What White Pact can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can detect and redact PII + harmful content before it reaches a log, and compare two models across all 6 trust dimensions.

The 27 tools it gives your agent

Extracted from the project's README - what WhitePact lets an agent do.

rai_scan: - Detect and redact PII + harmful content before it reaches a log
rai_trust_score: - Composite AI Trust Score (0-100) across 6 governance dimensions
rai_compliance: - NIST AI RMF / EU AI Act / ISO 42001 compliance evaluation
rai_hallucination: - Hallucination risk from hedging, consistency, unsupported claims
rai_cost_estimate: - USD cost of a model API call from token counts
rai_redteam_payloads: - Adversarial attack payloads (prompt injection, jailbreak, etc.)
rai_redteam_analyze: - Security report from model responses to red team payloads
rai_compare_models: - Compare two models across all 6 trust dimensions
rai_audit_summary: - Governance capability summary (tools, frameworks, attack vectors)
rai_health: - Status and module availability of the governance engine
rai_bias_evaluate: - Demographic bias across 6 probe dimensions with confidence intervals
rai_drift_check: - Trust score drift between a baseline and current evaluation

show all 27 tools

rai_passport_generate: - Verifiable, tamper-evident AI Passport for vendor risk assessment
rai_budget_check: - Spend vs. budget, per-team/model breakdown, month-end projection
rai_policy_check: - Text/response against a governance policy (blocklists, disclaimers)
rai_stream_scan: - PII/harm scan across streaming LLM output chunks
rai_benchmark: - Score responses against truthfulqa / bbq / hellaswag suites
rai_benchmark_prompts: - Question set for a benchmark suite
rai_model_route: - Cheapest model that can handle a task, with cost/quality tradeoff
rai_pii_report: - PII audit report by category with GDPR/CCPA remediation guidance
rai_incident_log: - Structured governance incident record for audit/SIEM
rai_eu_ai_act_classify: - EU AI Act risk tier classification with compliance roadmap
rai_iso42001_gap: - ISO/IEC 42001:2023 AI Management System gap analysis
rai_executive_summary: - Board-ready governance summary with RAG status indicators
rai_org_status: - Governance status snapshot: models, grades, compliance, risk
rai_webhook_status: - Webhook delivery health, failure analysis, remediation actions
rai_check_trust: - Free public Trust Index lookup for a third-party model/tool, before an agent invokes it - unlike every other tool above, which evaluates output the caller itsel

Latest releases

v1.2.6 · 2026-08-30

See CHANGELOG.md for the curated entry. · Supply-chain verification commands are documented in · docs/VERIFY_RELEASE.md. · stage only distributions for PyPI · prepare v1.2.6

v1.2.3 · 2026-08-19

See CHANGELOG.md for the curated entry for this version. · Supply chain verification (Phase 15): · sbom.cyclonedx.json (CycloneDX 1.6) attached to this release. · Build provenance: gh attestation verify <file> --owner…

v1.2.2 · 2026-08-12

04 · Who maintains White Pact

WhitePact is maintained by guruprasath-annadurai. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

repository: github.com/guruprasath-annadurai/whitepact
website: https://github.com/Guruprasath-Annadurai/Whitepact
category: security - ranked #75 of 216 actively-maintained security servers as of 2026-09-30.
release cadence: 5 releases in the last 90 days (latest 2026-08-30)
registry: io.github.Guruprasath-Annadurai/whitepact (active, first published 2026-08-12 · 2 versions)
packages: pypi:rai-governance-platform

06 · White Pact FAQ

Is White Pact still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-30 and it shipped 5 releases in the last 90 days. We re-verify nightly.

What can White Pact do?

With this server connected, an agent can detect and redact PII + harmful content before it reaches a log, and compare two models across all 6 trust dimensions.

How do I install White Pact?

Run `uvx rai-governance-platform`. The README documents 9 environment variables (RAI_API_URL, RAI_API_KEY, RAI_DB_PATH…) to set first. Set RAI_API_URL, RAI_API_KEY, RAI_DB_PATH, RAI_API_KEYS, RAI_AUTH_ENABLED, RAI_DB_URL, RAI_DATABASE_URL, RAI_REDIS_URL, RAI_OTEL_ENDPOINT before connecting. You can also paste the ready-made client config above.

Does White Pact run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to White Pact

Alternatives to White Pact

Maintained security servers if White Pact isn't the fit.

Pairs well with

Servers that cover what White Pact doesn't - only shown when the pairing reason fits the companion.

More security MCP servers · Lockkeeper · Coach Watts · Bug Bounty Intelligence · Honey Labs

More Python MCP servers · Qai Consultant MCP · OpenHire · 哨兵 · Omni Lpr · Data Profiler MCP · Hail · see all