B

npm:claude-prompt-optimizer-mcp

https://www.npmjs.com/package/claude-prompt-optimizer-mcp
85/100 · MCP Trust Grade · checked 3h ago · MCP 5.0.2

What it offers — 18 tools · Developer Tools

optimize_prompt

Analyze a raw prompt, detect ambiguities, compile an optimized version, score quality, and estimate cost across providers. Returns a PreviewPack for r

refine_prompt

Refine a prompt by answering blocking questions or providing manual edits. Re-runs analysis and returns updated PreviewPack.

approve_prompt

Approve the compiled prompt. Returns the final optimized prompt ready for use.

estimate_cost

Estimate token count and cost across providers for any prompt text. No session needed.

compress_context

Compress context (code, docs) by removing irrelevant sections. Returns pruned context with token savings.

check_prompt

Quick pass/fail check of a prompt. Returns score, top issues, and a suggestion. No compilation, no session.

configure_optimizer

Configure optimizer behavior: mode, threshold, strictness, default target, ephemeral mode, session limits. Supports config locking with passphrase pro

get_usage

Get current usage count, limits, remaining quota, and tier information.

prompt_stats

Get aggregated optimization statistics: total count, average score, top task types, estimated savings.

set_license

Activate a Pro or Power license key. Validates the Ed25519 signature offline and unlocks the corresponding tier.

license_status

Check current license status, tier, and expiry. Returns purchase link if no license is active.

classify_task

Classify a prompt by task type, reasoning complexity, risk level, and suggested profile. Free — no metering.

route_model

Route to the optimal model based on task complexity, risk, budget, and latency preferences. Returns recommendation with decision_path audit trail. Fre

pre_flight

Full pre-flight analysis: classify task, assess risk, route model, score quality. Returns complete decision bundle. Metered — counts as 1 optimization

prune_tools

Score and rank MCP tools by relevance to a task intent. Optionally prune low-relevance tools to save context tokens.

list_sessions

List all optimization sessions with metadata (no raw prompts). Free tool, not metered.

export_session

Export full session details including raw prompt. Free tool, not metered.

delete_session

Delete a single optimization session by ID. Returns deleted status. Free tool, not metered.

Spec / packaging20%100
Security (OWASP MCP)30%70
Maintenance / popularity20%83
Tool hygiene15%95
Transparency / provenance15%90

Findings

INFO Static analysis of npm package claude-prompt-optimizer-mcp@5.0.2 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:claude-prompt-optimizer-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:claude-prompt-optimizer-mcp grade B
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade B · wmcp.sh
[![MCP Trust Grade B](https://wmcp.sh/mcp/grade/npm%3Aclaude-prompt-optimizer-mcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Aclaude-prompt-optimizer-mcp)
<a href="https://wmcp.sh/mcp/grade/npm%3Aclaude-prompt-optimizer-mcp"><img src="https://wmcp.sh/mcp/grade/npm%3Aclaude-prompt-optimizer-mcp/badge.svg" alt="MCP Trust Grade B · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.