Clarifyprompt MCP Server

Context-aware MCP prompt compiler with a composable pipeline: clarify_with_user → ground_prompt OR optimize_prompt → critique_prompt, all in one call

Remote serverstreamable-http

What is the Clarifyprompt MCP MCP server?

Connect Clarifyprompt MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. 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. The clarifyprompt mcp mcp server is what makes that connection.

What the server does

A context-aware MCP prompt compiler that transforms vague prompts into platform-optimized prompts for 60+ AI platforms across 7 categories — grounded in your workspace signals (CLAUDE.md, AGENTS.md, .cursorrules, package.json), resolved intent, and the capabilities of the target model.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Accept — one click records save_outcome(accepted) from the panel, feeding the few-shot memory loop, and quietly tells the model the prompt was accepted
  • Clarification-aware — when the pre-clarify stage stops the chain with questions, the panel renders them (with suggested answers) instead of a diff
  • Fixed — explicit mode no longer silently dropped for small local models.** Compact system-prompt shaping used to trim the mode instructions entirely — so
  • Compile — a message/send with the raw prompt (plain text, or JSON { prompt, platform?, category?, … }) returns a task whose artifact carries the optimized
  • Endpoint — Purpose
  • Value — Behaviour
  • streamable-http — MCP Streamable HTTP over Node's built-in http (no new deps): stateful sessions (mcp-session-id), SSE streaming, a /health probe
  • a2a — Serve as an A2A (Agent-to-Agent) peer — agent card, JSON-RPC + SSE (see 1.12.0 above)
  • Transports — HTTP knobs (in streamable-http / a2a mode): CLARIFYPROMPT_HTTP_PORT (3000), CLARIFYPROMPT_HTTP_HOST (127.0.0.1 — localhost-only by default)
  • Cancellation — An AbortSignal is plumbed through the entire LLM path (simpleGenerate → chat → fetch, combined with the per-call timeout) and every engine stage
  • Progress — Include a progressToken in the compose_prompt request _meta and the server emits notifications/progress at each stage (clarify / optimize / ground /
  • Autocomplete — completion/complete resolves the template variables: {category} → the 7 category ids, {id} → platform ids scoped by the chosen {category}, {date} →

Credentials and setup notes

Configuration is passed through the environment: LLM_API_URL, CLARIFYPROMPT_A2A_BASE_URL, CLARIFYPROMPT_HTTP_HOST, CLARIFYPROMPT_HTTP_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Clarifyprompt MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Clarifyprompt MCP's toolset — Accept, Clarification-aware, Fixed and 10 more — is a fair guide to whether it matches your workflow. It is maintained by lumabyteco; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
Acceptone click records save_outcome(accepted) from the panel, feeding the few-shot memory loop, and quietly tells the model the prompt was accepted.
Clarification-awarewhen the pre-clarify stage stops the chain with questions, the panel renders them (with suggested answers) instead of a diff.
Fixedexplicit mode no longer silently dropped for small local models.** Compact system-prompt shaping used to trim the mode instructions entirely — so mode: "simple" had no effect on 3B-class models. Every mode now survives c
Compilea message/send with the raw prompt (plain text, or JSON { prompt, platform?, category?, … }) returns a task whose **artifact** carries the optimized prompt (text) plus the full structured compose result (data).
EndpointPurpose
ValueBehaviour
streamable-httpMCP Streamable HTTP over Node's built-in http (no new deps): stateful sessions (mcp-session-id), SSE streaming, a /health probe
a2aServe as an **A2A (Agent-to-Agent)** peer — agent card, JSON-RPC + SSE (see 1.12.0 above)
TransportsHTTP knobs (in streamable-http / a2a mode): CLARIFYPROMPT_HTTP_PORT (3000), CLARIFYPROMPT_HTTP_HOST (127.0.0.1 — localhost-only by default), CLARIFYPROMPT_HTTP_PATH (/mcp, streamable-http only).
CancellationAn AbortSignal is plumbed through the entire LLM path (simpleGenerate → chat → fetch, combined with the per-call timeout) and every engine stage. When a client sends notifications/cancelled for a compose_prompt call, the
ProgressInclude a progressToken in the compose_prompt request _meta and the server emits notifications/progress at each stage (clarify / optimize / ground / critique) with a monotonic counter and a human message like optimizing
Autocompletecompletion/complete resolves the template variables: {category} → the 7 category ids, {id} → platform ids scoped by the chosen {category}, {date} → days with traces, pack ids, memory scopes. (MCP completion applies to pr
CapabilitiesThe server now advertises resources (with templates) and completions at initialize. New deterministic npm run test:resources battery locks the surface.

How to install the Clarifyprompt MCP MCP server

{
  "mcpServers": {
    "clarifyprompt": {
      "command": "npx",
      "args": ["-y", "clarifyprompt-mcp"],
      "env": {
        "LLM_API_URL": "your-value",
        "CLARIFYPROMPT_A2A_BASE_URL": "your-value",
        "CLARIFYPROMPT_HTTP_HOST": "your-value",
        "CLARIFYPROMPT_HTTP_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
LLM_API_URLEndpoint or connection string the server talks to.Yes
CLARIFYPROMPT_A2A_BASE_URLEndpoint or connection string the server talks to.Yes
CLARIFYPROMPT_HTTP_HOSTEndpoint or connection string the server talks to.Optional
CLARIFYPROMPT_HTTP_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Clarifyprompt MCP to Accept.
  • Use Clarifyprompt MCP to Clarification-aware.
  • Use Clarifyprompt MCP to Fixed.

Frequently asked questions

It connects Clarifyprompt MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (Accept, Clarification-aware, Fixed, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Clarifyprompt MCP directly.