optimize_promptOptimize a prompt for a specific AI platform. Context-aware: auto-gathers workspace signals (CLAUDE.md / AGENTS.md / .cursorrules / package.json), res
list_categoriesList all available prompt optimization categories with platform counts including custom platforms
list_platformsList available platforms for a category, including custom registered platforms.
list_modesList available output modes for prompt optimization
register_platformRegister a new custom AI platform for prompt optimization.
update_platformUpdate a custom platform or add/override instructions on a built-in platform.
unregister_platformRemove a custom platform, or clear instruction overrides on a built-in.
inspect_contextPreview the ContextBundle (workspace rules, frameworks, target-model capabilities, resolved analysis, session history) without running optimization. R
list_tracesList recent optimization traces from the local tracer. Summary only; use get_trace for full records.
get_traceFetch the full trace for an optimization ID, including system prompt + output. Looks back 7 days by default.
save_outcomeTell ClarifyPrompt whether an optimization
memory_searchSemantic search over the persistent memory store. Returns facts, pack chunks, and past optimizations ranked by vector similarity to the query. Useful
memory_rememberExplicitly add a fact to persistent memory. Use when the user says something the engine should remember across sessions (preferences, conventions, pro
memory_forgetInvalidate (soft-delete) a fact by its id. The fact is marked invalidated_at = now and won
memory_list_factsList live (non-invalidated) facts in persistent memory, optionally filtered by scope and predicate. Sorted by most-recently-observed first. Useful for
explain_last_curationRender a human-readable explanation of the Context Curator
load_knowledge_packLoad a knowledge pack — a markdown document with optional YAML frontmatter — into the persistent memory store. The pack is chunked by heading, each ch
list_packsList knowledge packs currently loaded in the persistent memory store.
+5 more tools
We re-grade npm:clarifyprompt-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.
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
readOnly vs observed behavior) layer on via the wmcp.sh proxy.