// MCP TOOL REFERENCE

CLARIFYPROMPT TOOLS

28 tools from the Clarifyprompt MCP Server, categorised by risk level.

// ALL 28 CLARIFYPROMPT TOOLS

READ 20 tools

Read clarify_with_user Given an ambiguous draft prompt, return 1–3 targeted clarifying questions instead of guessing. Each questio... Read clarity Is the ask unambiguous? Could two readers interpret it the same way? Read critique_prompt LLM-as-judge for a prompt. Scores it 0–10 across 5 default dimensions (clarity, specificity, intent_alignme... Read explain_last_curation Render a human-readable explanation of the Context Curator Read format_fitness Is the requested output format appropriate for the platform/category and downstream use? Read get_trace Fetch the full trace for an optimization ID, including system prompt + output. Looks back 7 days by default. Read ground_prompt Optimize a prompt against EXPLICIT caller-provided grounding sources (a spec, a transcript excerpt, an RFC,... Read inspect_context Preview the ContextBundle (workspace rules, frameworks, target-model capabilities, resolved analysis, sessi... Read intent_alignment Does the prompt match what the user actually wants to achieve? (If an originalPrompt is provided, judge whe... Read length_appropriateness Is the prompt the right length — neither vague-and-too-short nor padded-and-too-long? Read list_categories List all available prompt optimization categories with platform counts including custom platforms Read list_modes List available output modes for prompt optimization Read list_packs List knowledge packs currently loaded in the persistent memory store. Read list_platforms List available platforms for a category, including custom registered platforms. Read list_traces List recent optimization traces from the local tracer. Summary only; use get_trace for full records. Read load_knowledge_pack Load a knowledge pack — a markdown document with optional YAML frontmatter — into the persistent memory sto... Read memory_list_facts List live (non-invalidated) facts in persistent memory, optionally filtered by scope and predicate. Sorted ... Read memory_search Semantic search over the persistent memory store. Returns facts, pack chunks, and past optimizations ranked... Read optimize_prompt Optimize a prompt for a specific AI platform. Context-aware: auto-gathers workspace signals (CLAUDE.md / AG... Read specificity Does it pin down concrete details (audience, format, scope, constraints) instead of leaving them implicit?

WRITE 4 tools

Write memory_remember Explicitly add a fact to persistent memory. Use when the user says something the engine should remember acr... Write register_platform Register a new custom AI platform for prompt optimization. Write save_outcome Tell ClarifyPrompt whether an optimization Write update_platform Update a custom platform or add/override instructions on a built-in platform.

DESTRUCTIVE 3 tools

Destructive memory_forget Invalidate (soft-delete) a fact by its id. The fact is marked invalidated_at = now and won Destructive unload_pack Remove a loaded knowledge pack (and all its chunks + embeddings) from the memory store. Destructive unregister_platform Remove a custom platform, or clear instruction overrides on a built-in.

EXECUTE 1 tools

Execute compose_prompt Run the canonical ClarifyPrompt pipeline in ONE call: clarify (optional pre-stage) → ground OR optimize (co...

// RUNNING THIS SERVER

The managed route: connect Clarifyprompt through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y clarifyprompt-mcp

// FAQ

How many tools does the Clarifyprompt MCP server have? +

The Clarifyprompt MCP server exposes 28 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Clarifyprompt tools? +

Route the Clarifyprompt server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Clarifyprompt tools fall into? +

Clarifyprompt tools are categorised as Read (20), Write (4), Destructive (3), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.