Score, enforce policy, lock config, and audit every prompt decision — before it reaches any LLM.
Deterministic. Offline. Hash-chained audit trail. Policy enforcement built in.
Routes across 4 providers · 11 models
Anthropic · OpenAI · Google · Perplexity
See all supported models →Every prompt goes straight to the model with no quality check, no cost estimate, and no governance. Here’s what that costs you.
“Make the code better” gives the model no constraints, no target, and no success criteria — leading to unpredictable results that cost 3× what they should.
Most teams have no idea how many tokens their prompts consume across Haiku, Sonnet, Opus, GPT-4o, and Gemini — until the bill arrives.
Without routing logic, every prompt hits the same expensive model. A simple factual question doesn’t need Opus. PCP routes it to Gemini Flash instead — 94% cheaper.
Claude starts working immediately on whatever you type. There’s no review step, no policy check, and no way to enforce prompt standards across a team.
Enterprise compliance needs to know what prompts ran, when, at what risk score, and what policy decision was made. There’s no log of any of that today.
Five steps from rough prompt to production-ready. All analysis is deterministic — no AI calls inside.
Get a quality score (0–100) with dimensional breakdown. Every deduction has a traceable reason.
Deterministic rules catch scope explosion, missing constraints, hallucination risk, and vague instructions.
Adds role, goal, constraints, workflow, and output format. Choose your target: Claude XML, OpenAI system/user, or Markdown.
Estimates token count and cost across 11 models from Anthropic, OpenAI, Google, and Perplexity.
Review the compiled result, answer blocking questions if needed, then approve. Nothing executes without your sign-off.
See a vague prompt get analyzed, improved, routed to the right model, and approved — all without a single LLM call.
The governance layer you need before approving AI in production. All managed through a license-gated Enterprise Console.
A web-based governance control panel, accessible only with a valid Enterprise license key. Configure policy, inspect audit logs, build custom rules, and manage session retention — all from one authenticated place. License verification is fully offline.
Lock your governance config with a passphrase derived from your enterprise license. No one can change policy, strictness, or audit settings without authenticating through the console. Every attempt — successful or blocked — is audit-logged.
Switch from advisory to enforce mode. BLOCKING rules (built-in + custom) gate every prompt. Risk threshold gating blocks high-risk approvals. Deterministic — same input, same verdict, every time.
Every action generates a JSONL audit entry with SHA-256 hash chaining. If any line is deleted or modified, the chain breaks. Local-only, opt-in, never stores prompt content. Explore and verify your audit logs visually in the Enterprise Console.
Delete individual sessions or bulk-purge by age policy. Dry-run mode previews what would be removed. A configurable retention window protects your newest sessions. Purge only touches session files — config, audit, and license are never deleted.
Every prompt reaches 90/100 after optimization. Average improvement: +32 points. Deterministic — same prompt, same result, every time.
| Prompt | Type | Before | After | Δ | Model | Blocked? |
|---|---|---|---|---|---|---|
| “make the code better” | other | 48 | 90 | +42 | sonnet | — |
| “fix the login bug” | debug | 51 | 90 | +39 | opus | ⚠ 3 BQs |
| Multi-task (4 in 1) | refactor | 51 | 90 | +39 | opus | ⚠ 3 BQs |
| Auth middleware (well-specified) | refactor | 76 | 90 | +14 | opus | — |
| Retry logic (precise) | code | 61 | 90 | +29 | sonnet | — |
| Create REST API server | create | 51 | 90 | +39 | opus | ⚠ 2 BQs |
| LinkedIn post (technical) | writing | 59 | 90 | +31 | sonnet | — |
| Redis vs Memcached research | research | 56 | 90 | +34 | sonnet | — |
| Data transformation (CSV) | data | 56 | 90 | +34 | haiku | — |
BQ = Blocking Question. Prompts in ANALYZING state require refinement before compilation completes. All results are deterministic.
Every result is reproducible, every decision is auditable, and nothing leaves your machine.
Extensively tested. Fully open for inspection. Run the suite yourself to verify.
Free tier includes 10 optimizations, unlimited scoring, and all 20 tools. No credit card required.
Run the same scoring, routing, and policy enforcement from your terminal or CI pipeline. No MCP needed.
Classify, score, route, and enforce policy in one call. The single command that covers 90% of use cases.
pcp preflight — full pre-flight analysispcp optimize — optimization pipelinepcp check — quick quality checkpcp score — detailed scoring breakdownpcp classify — task classificationpcp route — model routingpcp cost — cost estimationpcp compress — context compressionpcp config — show governance configpcp doctor — validate environment
pcp)CLI and MCP respect the same governance config. Policy enforcement applies identically across all interfaces.
Add to any MCP-compatible client: Claude Code, Cursor, or Windsurf.
Works with any codebase — Python, Java, Go, Rust, or any language. Node.js is only needed to run the MCP server, not your project.
{ "mcpServers": { "prompt-optimizer": {
"command": "npx",
"args": ["-y", "claude-prompt-optimizer-mcp"]
}}}
npm install -g claude-prompt-optimizer-mcp
curl -fsSL https://prompt-control-plane.pages.dev/install.sh | bash