Skip to content
Agentmart
Submit a tool

Clarifyprompt

AI prompt optimization for 58+ platforms across 7 categories with custom platforms

Connector by LumabyteCo · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 13
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lumabyteco-clarifyprompt

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

AI prompt optimization for 58+ platforms across 7 categories with custom platforms

Use cases: prompt-engineering, llm-evaluation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
12 read · 8 write · 3 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 23

Read from the source code; the running server may list different tools.

Read 12 · Look things up without changing anything.

  • clarify_with_user
  • critique_prompt
  • explain_last_curation
  • get_trace
  • inspect_context
  • list_categories
  • list_modes
  • list_packs
  • list_platforms
  • list_traces
  • memory_list_facts
  • memory_search

Write 8 · Create, change, send or run things.

  • compose_prompt
  • ground_prompt
  • load_knowledge_pack
  • memory_remember
  • optimize_prompt
  • register_platform
  • save_outcome
  • update_platform

Delete 3 · Delete, drop, revoke or wipe things.

  • memory_forget
  • unload_pack
  • unregister_platform

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • LLM_API_KEY

Other settings (environment variables or headers).

  • LLM_API_URL
  • LLM_MODEL

Network hosts it talks to 18

  • ai.google.dev · found in code
  • api.exa.ai · found in code
  • api.search.brave.com · found in code
  • api.tavily.com · found in code
  • blog.google · found in code
  • docs.midjourney.com · found in code
  • elevenlabs.io · found in code
  • github.com · found in code
  • glama.ai · found in code
  • google.serper.dev · found in code
  • help.openai.com · found in code
  • klingai.com · found in code
  • ollama.com · found in code
  • platform.openai.com · found in code
  • runway.com · found in code
  • seed.bytedance.com · found in code
  • serpapi.com · found in code
  • suno.com · found in code

Files it touches

  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (23)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • clarify_with_userAsk clarifying questionsread-only

    Given an ambiguous draft prompt, return 1–3 targeted clarifying questions instead of guessing. Each question carries a `suggested_answer` you can accept verbatim to keep moving, an optional 2–4 quick-pick `options` list, and a `dimension` tag (audience/scope/format/length/tone/constraints/goal/platform). When the analyzer is highly confident AND the prompt is non-trivially long, the tool short-circuits with `clarificationNeeded: false` so callers can pipeline this in front of optimize_prompt without paying a latency tax on every call. Pass `force: true` to always generate questions. Pass `elic…

  • compose_promptCompose the full pipeline

    Run the canonical ClarifyPrompt pipeline in ONE call: clarify (optional pre-stage) → ground OR optimize (core) → critique (optional post-stage) → optional auto-revise. Use this when you want the four-tool happy path without orchestrating five round-trips. Short-circuits if `pre_clarify` surfaces questions — caller answers and re-calls. When `sources` is non-empty the chain takes the strict ground_prompt branch; otherwise it goes through optimize_prompt. When `auto_revise` is true and critique returns a non-accept verdict with an improved rewrite, `final_prompt` is the rewrite. The `stages` arr…

  • critique_promptCritique a prompt (LLM-as-judge)read-only

    LLM-as-judge for a prompt. Scores it 0–10 across 6 default dimensions (clarity, specificity, intent_alignment, format_fitness, length_appropriateness, plain_language) — or your own custom criteria — and returns per-dimension rationale + concrete suggestions, an overall score, and a verdict (`accept` / `revise` / `reject`). When the score is below `revise_threshold` (default 7.0), the tool also returns an `improvedPrompt` you can use as a drop-in replacement. Use it pre-flight (is this prompt good enough for the expensive model?), postmortem (was the prompt the cause of a bad output?), or to A/…

  • explain_last_curationExplain the last curationread-only

    Render a human-readable explanation of the Context Curator's decisions for the most recent (or a specified) optimization. Shows every candidate that was considered, whether it was selected or rejected, why, and how many tokens it used against the budget. Use this when an output felt off and you want to understand which grounding sources the engine chose.

  • get_traceGet a full traceread-only

    Fetch the full trace for an optimization ID, including system prompt + output. Looks back 7 days by default.

  • ground_promptOptimize against explicit sources

    Optimize a prompt against EXPLICIT caller-provided grounding sources (a spec, a transcript excerpt, an RFC, an internal doc, etc.). Each source is pinned at the highest priority — above project rules, above pinned instructions — and tracked individually in the trace. Use this when you want the rewrite to cite specific material rather than letting the curator decide what's relevant. Requires at least one non-empty source; will error rather than silently fall through to optimize_prompt. Sources are capped at 4000 chars each so a single large paste can't dominate the budget.

  • inspect_contextInspect the context bundleread-only

    Preview the ContextBundle (workspace rules, frameworks, target-model capabilities, resolved analysis, session history) without running optimization. Returns the same bundle that optimize_prompt would assemble.

  • list_categoriesList categoriesread-only

    List all available prompt optimization categories with platform counts including custom platforms

  • list_modesList output modesread-only

    List available output modes for prompt optimization

  • list_packsList loaded packsread-only

    List knowledge packs currently loaded in the persistent memory store.

  • list_platformsList platformsread-only

    List available platforms for a category, including custom registered platforms.

  • list_tracesList optimization tracesread-only

    List recent optimization traces from the local tracer. Summary only; use get_trace for full records.

  • load_knowledge_packLoad a knowledge pack

    Load a knowledge pack — a markdown document with optional YAML frontmatter — into the persistent memory store. The pack is chunked by heading, each chunk embedded, and made available for semantic retrieval during subsequent optimize_prompt calls. Packs can come from a local file path, an HTTPS URL, or be passed inline as raw markdown. Bundled packs + authoring guide: https://github.com/LumabyteCo/clarifyprompt-mcp/tree/main/packs

  • memory_forgetForget a factcan change or delete data

    Invalidate (soft-delete) a fact by its id. The fact is marked invalidated_at = now and won't appear in future memory_search or grounding, but its history is preserved (bi-temporal soft-delete). Use `memory_list_facts` first to find the id you want to forget.

  • memory_list_factsList remembered factsread-only

    List live (non-invalidated) facts in persistent memory, optionally filtered by scope and predicate. Sorted by most-recently-observed first. Useful for inspecting what the engine knows, or finding fact ids to forget.

Show 8 more tools
  • memory_rememberRemember a fact

    Explicitly add a fact to persistent memory. Use when the user says something the engine should remember across sessions (preferences, conventions, project facts). Complements `save_outcome` reflection, which extracts facts implicitly — this is the explicit, user-driven path. Returns the new fact id, which can be passed to `memory_forget` later.

  • memory_searchSearch persistent memoryread-only

    Semantic search over the persistent memory store. Returns facts, pack chunks, and past optimizations ranked by vector similarity to the query. Useful for inspecting what ClarifyPrompt would retrieve for a given prompt, and for debugging curator decisions.

  • optimize_promptOptimize a prompt for a platform

    Optimize a prompt for a specific AI platform. Context-aware: auto-gathers workspace signals (CLAUDE.md / AGENTS.md / .cursorrules / package.json), resolves intent + category + recommended mode in a single analysis step, shapes the system prompt to the target model's capabilities, and grounds the rewrite in a priority-ordered Grounding Context. Supports 61 platforms across 7 categories (verifiedAt-dated packs), plus custom registered platforms. Category, platform, and mode are all optional — the engine chooses sane defaults from the analysis.

  • register_platformRegister a custom platform

    Register a new custom AI platform for prompt optimization.

  • save_outcomeRecord an outcome (accept / edit / reject)

    Tell ClarifyPrompt whether an optimization's output was accepted, edited, or rejected. Feeds two loops: (1) the session ring buffer so accepted prior outputs are injected as few-shot examples into future similar prompts, and (2) the persistent memory layer via reflection — on accept/edit, ClarifyPrompt extracts atomic facts from the interaction and stores them; on reject, recent reflection facts from this session are invalidated. Reflection uses the same LLM you've configured; expect a 1–3s latency on local models.

  • unload_packUnload a knowledge packcan change or delete data

    Remove a loaded knowledge pack (and all its chunks + embeddings) from the memory store.

  • unregister_platformRemove a custom platform / clear overridescan change or delete data

    Remove a custom platform, or clear instruction overrides on a built-in.

  • update_platformUpdate a platform

    Update a custom platform or add/override instructions on a built-in platform.

Signals

Stars
13
Forks
2
Open issues
0
Last commit
Oct 6, 2026 (22 days ago)
Last release
Jun 22, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.LumabyteCo/clarifyprompt
Version
1.1.3
Auth
API key
Packages
npm clarifyprompt-mcp
License
Apache-2.0
Repository
github.com/LumabyteCo/clarifyprompt-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Clarifyprompt MCP server. Agent Mart. https://agentmart.dev/connectors/lumabyteco-clarifyprompt (last updated 2026-10-24)