MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Clarifyprompt is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
14
downloads a day
local
runs on your machine
477
downloads in 30d
What it does
Context-aware MCP prompt compiler with a composable pipeline: clarify_with_user → ground_prompt OR optimize_prompt → critique_prompt, all in one call via compose_prompt. Persistent memory, knowledge packs, explicit token-budget curation, reflective learni
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'LLM_API_URL=${LLM_API_URL}' --env 'LLM_MODEL=${LLM_MODEL}' --transport stdio clarifyprompt-mcp '--' npx -y clarifyprompt-mcp
# 2 — ask your agent for something these tools do
# optimize_prompt, list_categories, list_platforms and 20 more
It needs LLM_API_URL, LLM_MODEL: this reads them from your environment, so export them first.
Clarifyprompt costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LUAll 1 server
lumabyteco1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Clarifyprompt as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads LLM_API_URL (LLM API endpoint URL (OpenAI-compatible or Anthropic)), LLM_MODEL (Model name/ID to use for optimization) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx LLM_API_URL …, setx LLM_MODEL … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'LLM_API_URL=${LLM_API_URL}' --env 'LLM_MODEL=${LLM_MODEL}' --transport stdio clarifyprompt-mcp '--' npx -y clarifyprompt-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs settings only you can give it: LLM_API_URL — LLM API endpoint URL (OpenAI-compatible or Anthropic); LLM_MODEL — Model name/ID to use for optimization. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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…
No parameter schema on file.
List all available prompt optimization categories with platform counts including custom platforms
No parameter schema on file.
List available platforms for a category, including custom registered platforms.
No parameter schema on file.
List available output modes for prompt optimization
No parameter schema on file.
Register a new custom AI platform for prompt optimization.
No parameter schema on file.
Update a custom platform or add/override instructions on a built-in platform.
No parameter schema on file.
Remove a custom platform, or clear instruction overrides on a built-in.
No parameter schema on file.
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.
No parameter schema on file.
List recent optimization traces from the local tracer. Summary only; use get_trace for full records.
No parameter schema on file.
Fetch the full trace for an optimization ID, including system prompt + output. Looks back 7 days by default.
No parameter schema on file.
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,…
No parameter schema on file.
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.
No parameter schema on file.
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…
No parameter schema on file.
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.
No parameter schema on file.
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.
No parameter schema on file.
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…
No parameter schema on file.
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…
No parameter schema on file.
List knowledge packs currently loaded in the persistent memory store.
No parameter schema on file.
Remove a loaded knowledge pack (and all its chunks + embeddings) from the memory store.
No parameter schema on file.
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…
No parameter schema on file.
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…
No parameter schema on file.
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…
No parameter schema on file.
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…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Clarifyprompt or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 1.16.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings2 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest4e80b48cc9e9de852bc5fa58a168efc6f86ad157ca4c825bd99f1da4f05881db
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (23 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| optimize_prompt | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_categories | no tags | |
| list_platforms | no tags | |
| list_modes | no tags | |
| register_platform | state-write | state-write: declares readOnlyHint: false |
| update_platform | state-write | state-write: declares readOnlyHint: false |
| unregister_platform | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| inspect_context | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_traces | no tags | |
| get_trace | untrusted-input | untrusted-input: keyword "fetch" |
| save_outcome | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| memory_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| memory_remember | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| memory_forget | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| memory_list_facts | no tags | |
| explain_last_curation | no tags | |
| load_knowledge_pack | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_packs | no tags | |
| unload_pack | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| clarify_with_user | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| ground_prompt | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| critique_prompt | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| compose_prompt | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest4e80b48cc9e9de85
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.16.0. Pin a release below and the command asks for exactly that one.
1.16.0
6 Oct 2026
latestNo release note was published with this version.
1.15.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Clarifyprompt can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.