Pricing

Pricing

Every plan includes the full scoring engine. Enterprise unlocks policy enforcement, audit trails, and config governance.

Free
₹0
forever
  • 10 lifetime optimizations
  • 5 per minute rate limit
  • All 20 tools
  • All 3 output formats
  • Unlimited scoring & checking
Start Free
Pro
₹499
per month (~$6)
  • 100 optimizations / month
  • 30 per minute rate limit
  • All 20 tools
  • Always-on mode
  • Offline license key
Get Pro
Power
₹899
per month (~$11)
  • Unlimited optimizations
  • 60 per minute rate limit
  • All 20 tools
  • Always-on mode
  • Priority support
Get Power
Enterprise
Custom
contact us
  • Unlimited optimizations
  • 120 per minute rate limit
  • Policy enforcement (advisory + enforce modes)
  • Hash-chained audit trail (JSONL, hash-chained)
  • Config lock with passphrase protection
  • Custom rules engine (up to 25 rules)
  • Session lifecycle management
  • Session retention policies (auto-purge)
  • Dedicated support
Contact Sales See all Enterprise features

Full Feature Comparison

Every tool, every tier. All 20 tools are available on all plans — metering applies only to optimization calls.

Feature Free Pro Power Enterprise
Limits & Rate
Monthly optimizations 10 lifetime 100 / mo Unlimited Unlimited
Rate limit 5 / min 30 / min 60 / min 120 / min
Always-on mode — ✓ ✓ ✓
Analysis Tools
Full optimization pipeline metered ✓ ✓ ✓ ✓
Quick quality check free ✓ ✓ ✓ ✓
Task classification free ✓ ✓ ✓ ✓
Routing Tools
Model routing free ✓ ✓ ✓ ✓
Pre-flight analysis metered ✓ ✓ ✓ ✓
Refinement Tools
Iterative refinement metered ✓ ✓ ✓ ✓
Approval gate free ✓ ✓ ✓ ✓
Cost & Compression Tools
Multi-provider cost estimation free ✓ ✓ ✓ ✓
Context compression free ✓ ✓ ✓ ✓
Tool relevance pruning free ✓ ✓ ✓ ✓
Configuration Tools
Settings & configuration free ✓ ✓ ✓ ✓
Usage tracking free ✓ ✓ ✓ ✓
Optimization statistics free ✓ ✓ ✓ ✓
License Tools
License activation free ✓ ✓ ✓ ✓
License status check free ✓ ✓ ✓ ✓
Session Tools
Session listing free ✓ ✓ ✓ ✓
Session export free ✓ ✓ ✓ ✓
Session deletion free ✓ ✓ ✓ ✓
Bulk session purge free ✓ ✓ ✓ ✓
Enterprise-Only Governance
Policy Enforcement — — — ✓
Audit Logging — — — ✓
Config Lock — — — ✓
Custom Rules — — — ✓
Session Retention Policies — — — ✓

Enterprise Features

The governance layer you need before approving AI in production.

🛡 Policy Enforcement

Switch from advisory mode (flags issues) to enforce mode (blocks prompts that fail policy). BLOCKING rules — both built-in and custom — gate every optimization. Risk threshold gating blocks high-risk approvals above a configurable score. Deterministic: same input produces the same verdict every time.

How to enable
Enterprise Console → Policy Enforcement → set mode to Enforce, strictness to Standard → Copy Command → Paste into Claude
What happens when a prompt is blocked
Prompt blocked → risk score 72 exceeds threshold (60) Triggered rules: ungrounded factual claims, autonomous execution without safety constraints Recommendation: add source context and safety constraints Exit code 3 (CLI) · policy_violation error (MCP)

See full response schema in docs →

📜 Audit Logging

Every action generates a JSONL audit entry with SHA-256 hash chaining. If any line is deleted or modified, the chain breaks and unauthorized changes are detectable. Local-only, opt-in, and never stores raw prompt content. Answers the question: who changed what, when, and was it allowed?

How to enable
Enterprise Console → Policy Enforcement → enable audit trail toggle → Copy Command → Paste into Claude
What gets logged
Every entry records: timestamp, action, request ID, tier, risk score, verdict Each entry is SHA-256 chained to the previous — delete or modify any line and the chain breaks Events: optimize, approve, delete, purge, configure, license activate Outcomes: success, blocked, error

See JSONL format reference in docs →

🔒 Policy-Locked Configuration

Lock your governance configuration so it can only be changed through the Enterprise Console. The lock passphrase is automatically derived from your enterprise license key — no separate secret to remember. Once locked, any attempt to change policy, strictness, threshold, or audit settings without the correct passphrase is blocked and audit-logged. Integrity-protected: the lock state itself is hash-verified.

How to enable
Open the Enterprise Console → Policy Enforcement → Generate Lock Command → Paste into Claude
What happens on unauthorized change
Configuration change attempted while locked → blocked The attempt is audit-logged (if audit trail is enabled) Unlock requires the original passphrase via Enterprise Console

🖥 Web-Based Admin Console

A dedicated governance console hosted at prompt-control-plane.pages.dev/admin.html — accessible only with a valid Enterprise license key. Authentication is fully offline (Ed25519 signature verification in the browser), so your key is never transmitted anywhere. The console generates all governance commands for you — policy mode, audit settings, config lock/unlock, custom rules, and session purges — eliminating the need to write commands by hand. Config lock passphrases are automatically derived from your license key, meaning your lock is cryptographically tied to your license: change policy only via the console, change it nowhere else.

Access
prompt-control-plane.pages.dev/admin.html → Enter Enterprise license key → Authenticated
What you get
✓ License-gated: enterprise keys only, verified offline ✓ Policy configurator — generates enforce/advisory commands ✓ Audit log explorer — paste audit.log, verify hash chain visually ✓ Custom rules builder — add/export rules without writing JSON ✓ Session manager — configure purge policies with dry-run preview ✓ Config lock — passphrase auto-derived from your license key ✓ Sign out clears session (sessionStorage, never persisted)

📋 Custom Rules

Define your own regex-based rules that run on every prompt. Build them visually in the Enterprise Console — which validates regex syntax, enforces the schema, and exports a ready-to-use JSON file. Each rule specifies a match pattern, severity (BLOCKING or NON-BLOCKING), a risk dimension (hallucination, constraint, underspec, or scope), and a risk weight. Up to 25 custom rules. Rules are hashed for reproducibility and included in session exports.

How to deploy rules
Enterprise Console → Custom Rules → build rules in visual editor → Copy & Deploy → paste into any AI assistant connected to PCP → rules active instantly
Example: block prompts containing email addresses
Enterprise Console → Custom Rules → New Rule Name: "Flag PII in prompts" Pattern: email regex match Severity: BLOCKING Risk dimension: constraint Weight: 20 (high priority) → Deploy to any connected AI assistant
Validate with CLI
pcp doctor

See full rule schema in docs →

🗑 Session Retention Policies

Auto-purge sessions older than a configurable retention period. Dry-run mode previews what would be deleted before committing. A configurable retention window protects your newest sessions from purge. Only session files are affected — config, audit logs, and license data are never deleted.

How to use
Enterprise Console → Session Management → set age, retention window, dry-run → Copy Command → Paste into Claude
Example dry-run preview
Dry run: 12 sessions matched, 5 protected by retention window 7 sessions would be deleted (oldest: Nov 2025, newest: Dec 2025) Run again without dry-run to execute the purge

Built for Enterprise Trust

Addressing the concerns your security and compliance teams will ask about.

Security

  • Zero LLM calls inside — prompts never leave your machine
  • No cloud services, no telemetry, no phone-home
  • Runs entirely on localhost via MCP stdio transport
  • Ed25519 offline license validation — no network needed
  • Config lock with SHA-256 hashed passphrase protection

Privacy

  • All data stored locally on your machine
  • No user accounts, no email collection, no PII stored
  • License keys contain only: tier, dates, license_id
  • Audit log never stores raw prompts or compiled outputs
  • Works behind corporate VPNs and air-gapped networks

Compliance & Governance

  • Deterministic — same input produces same output, always
  • Hash-chained audit trail with hash-chained JSONL entries
  • Policy enforcement blocks non-compliant prompts at approval
  • Reproducible exports with rule-set hashes for audit
  • Source-available — full code review available on GitHub

Deployment

  • No infrastructure to manage — runs as a local process
  • Compatible with Claude Code, Cursor, Windsurf, and any MCP client
  • No database, no containers, no cloud accounts required
  • Single npm install — works on macOS, Linux, and Windows
  • Zero dependencies on external AI services

Frequently Asked Questions

Common questions about plans, billing, and enterprise features.

What counts as an "optimization"?
Only three actions count against your quota: running a full optimization, iterative refinement, and pre-flight analysis. Everything else — quality checks, task classification, model routing, cost estimation, context compression, and session management — is always free on every tier.
Do I need an account to use the free tier?
No. The free tier works out of the box with zero configuration. No account, no API key, no credit card. Just install the MCP server and start using it.
How does the license key work?
License keys use Ed25519 asymmetric signatures and are validated entirely offline. No phone-home, no account server. The key contains your tier and expiry date, cryptographically signed. Activate it once and it works until expiry.
Can I switch between tiers?
Yes. Activate a new license key and your limits update immediately. License keys are cryptographically verified offline — no server call needed. Downgrading to free requires no action — just let the key expire.
What happens when I hit the free tier limit?
Metered tools return a clear error with your current usage, the limit, and purchase URLs for Pro and Power tiers. Non-metered tools continue working without restriction.
Is enterprise self-hosted or cloud?
Everything runs locally. There is no cloud component. The MCP server runs on your machine, all data stays on your filesystem, and audit logs are local JSONL files. Enterprise just unlocks governance features — it does not change the deployment model.

Ready to get started?

Start free with 10 optimizations. Upgrade anytime with an offline license key.

Start Free Contact Enterprise