PromptKingPromptKing MCP Governance Port

One URL. Any agent.
Verifiable receipts.

PromptKing governs AI agents across six vendor surfaces using a single MCP endpoint. Paste the URL into any MCP-compatible client — your agent is governed in 60 seconds.

This page and the start_here tool teach the same protocol. Humans read the page; agents read the tool. Same truth.

MCP Endpoint

https://www.promptking32.com/api/mcp/mcp

Paste into Claude Desktop, Cursor, or any MCP client. OAuth connects on first call.

How it works — out-of-path

System Context — Out-of-Path Architecture

Your AI Agent
direct————→
Vendor API
PromptKing

PromptKing

Metadata-onlyOut-of-path

↑ consumes metadata · emits decisions ↓

Governance Decisions

Evidence Receipts (SHA-256)

MCP Governance Signals

↓ Your enforcement stack (SIEM · IT governance · vendor controls)

PromptKing does not touch agent traffic. Decisions travel — PromptKing does not.

The four checkpoints

CHK-0Discover

Agent calls start_here. The port returns the governance contract: what tools exist, what the protocol expects, how to enroll. The agent learns the port without human configuration.

CHK-1Enroll

Agent registers via enroll or register_agent. Receives an agent ID, correlation ID, and autonomy tier. Identity is established — every subsequent call is attributed.

CHK-2Check Policy

Before acting, the agent declares intent and cost via check_policy. The policy engine evaluates against org rules and returns a verdict: ALLOWED, APPROVAL_REQUIRED, or MODEL_RESTRICTION. No enforcement — the agent decides whether to proceed.

CHK-3Report Outcome

After acting, the agent reports what happened via report_outcome. An evidence receipt is issued with a SHA-256 integrity hash. Append-only — the receipt exists forever, independently verifiable at /verify/[id].

18 tools

Governance Consultation

start_hereSelf-teaching protocol — agents learn the port
enrollRegister an agent with identity + autonomy tier
check_policyCHK-2: evaluate an action against org policy
report_outcomeCHK-3: declare outcome, receive evidence receipt

Intelligence Readers

get_overviewOrg-level KPIs: spend, utilization, savings
get_seat_fleetPer-seat detail: plan, cost, recommendation
get_seat_detailDeep dive on a single seat
get_savings_opportunitiesRanked rightsizing recommendations
get_github_creditsGitHub AI Credits burn rate + model breakdown
get_governance_scoresWatsonx model governance health
get_executive_reportCFO / COO / CRO persona reports
get_forecast30-day spend forecast with variance bands

Governance Readers

get_trajectoryFull trajectory with linked governance artifacts
get_trajectory_statusArchetype, cycles, cost, recent decisions
get_decision_receiptSingle policy decision as structured receipt
list_containment_signalsActive containment events for a trajectory

Agent Identity

register_agentCHK-1: register with SPIFFE identity + autonomy tier

Live proof

Every governed run produces a receipt. Every receipt is independently verifiable — the hash is recomputed in your browser, not by our server.

Verify a real receipt →

Protocol stats (live)

Loading live stats...

Numbers are live production counts — early-stage, honest, not inflated.

What we never touch

PromptKing processes metadata only — agent identity, cost declarations, policy verdicts, and governance signals. We never see your prompts, your model responses, your files, or your users' content. We never sit between your agent and the vendor API. Decisions travel. PromptKing does not.

← HomepageRead: Six Models. One Law. Six Receipts. →
MCP Governance Port — PromptKing | PromptKing AI FinOps