Context-aware MCP prompt compiler with a composable pipeline: clarify_with_user → ground_prompt OR optimize_prompt → critique_prompt, all in one call
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.
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.
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.
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 acceptedClarification-aware — when the pre-clarify stage stops the chain with questions, the panel renders them (with suggested answers) instead of a diffFixed — explicit mode no longer silently dropped for small local models.** Compact system-prompt shaping used to trim the mode instructions entirely — soCompile — a message/send with the raw prompt (plain text, or JSON { prompt, platform?, category?, … }) returns a task whose artifact carries the optimizedEndpoint — PurposeValue — Behaviourstreamable-http — MCP Streamable HTTP over Node's built-in http (no new deps): stateful sessions (mcp-session-id), SSE streaming, a /health probea2a — 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 stageProgress — 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} →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.
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.
| Tool | What it does |
|---|---|
| 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 mode: "simple" had no effect on 3B-class models. Every mode now survives c |
| Compile | a 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). |
| 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), CLARIFYPROMPT_HTTP_PATH (/mcp, streamable-http only). |
| Cancellation | An 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 |
| Progress | Include 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 |
| Autocomplete | completion/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 |
| Capabilities | The server now advertises resources (with templates) and completions at initialize. New deterministic npm run test:resources battery locks the surface. |
{
"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.
| Variable | Description | Required |
|---|---|---|
| LLM_API_URL | Endpoint or connection string the server talks to. | Yes |
| CLARIFYPROMPT_A2A_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| CLARIFYPROMPT_HTTP_HOST | Endpoint or connection string the server talks to. | Optional |
| CLARIFYPROMPT_HTTP_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.