Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional. Bearer pk_… PromptArch API key — required only for promptarch_generate_artifact and promptarch_enhance_prompt; lint and list work without it.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Enhance a raw prompt with PromptArch's Prompt Enhancer: PromptArch asks 1-3 targeted clarifying questions, then rewrites the prompt from the person's answers, optimized for target_model. If this client supports MCP elicitation, the questions appear to the person as a form inside this call. Otherwise call once with just `prompt` to get the questions (free), ask the person, and call again with `questions` and `answers`. Never answer the questions yourself. The enhancement costs 5 credits; questions are free. Requires a PromptArch API key configured as an Authorization: Bearer pk_... header on this MCP server.
The raw prompt to enhance.
Second call only: the person's own answers, keyed by question id (e.g. {"q1": "..."}).
Second call only: the questions JSON exactly as this tool returned it.
The model the enhanced prompt is for (e.g. Claude Opus 5.5, GPT-5). Default: generic, no model-specific optimization.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Enhance a raw prompt with PromptArch's Prompt Enhancer: PromptArch asks 1-3 targeted clarifying questions, then rewrites the prompt from the person's answers, optimized for target_model. If this client supports MCP elicitation, the questions appear to the person as a form inside this call. Otherwise call once with just `prompt` to get the questions (free), ask the person, and call again with `questions` and `answers`. Never answer the questions yourself. The enhancement costs 5 credits; questions are free. Requires a PromptArch API key configured as an Authorization: Bearer pk_... header on this MCP server.
| Argument | Type | Description |
|---|---|---|
| prompt* | string | The raw prompt to enhance. |
| answers | object | Second call only: the person's own answers, keyed by question id (e.g. {"q1": "..."}). |
| questions | array | Second call only: the questions JSON exactly as this tool returned it. |
| target_model | string | The model the enhanced prompt is for (e.g. Claude Opus 5.5, GPT-5). Default: generic, no model-specific optimization. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"maxLength": 10000,
"minLength": 10,
"description": "The raw prompt to enhance."
},
"answers": {
"type": "object",
"description": "Second call only: the person's own answers, keyed by question id (e.g. {\"q1\": \"...\"}).",
"propertyNames": {
"type": "string",
"maxLength": 20
},
"additionalProperties": {
"type": "string",
"maxLength": 2000
}
},
"questions": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"question"
],
"properties": {
"id": {
"type": "string",
"maxLength": 20
},
"question": {
"type": "string",
"maxLength": 500
}
}
},
"maxItems": 5,
"minItems": 1,
"description": "Second call only: the questions JSON exactly as this tool returned it."
},
"target_model": {
"type": "string",
"maxLength": 100,
"description": "The model the enhanced prompt is for (e.g. Claude Opus 5.5, GPT-5). Default: generic, no model-specific optimization."
}
}
}Generate an AI agent context artifact (e.g. context_pack, claude_md) from a project description. Requires a PromptArch API key configured as an Authorization: Bearer pk_... header on this MCP server. Consumes credits.
| Argument | Type | Description |
|---|---|---|
| artifact* | string | Artifact id. See promptarch_list_artifact_types. Other Studio artifact types need artifact-specific inputs this tool does not accept. |
| commands | string | |
| tech_stack | string | |
| project_name* | string | |
| target_model | string | Target model family (default Claude). |
| repo_structure | string | Directory tree or structure summary. Max 1900 chars: summarize a large repo rather than pasting a full tree. |
| coding_conventions | string | Conventions, invariants, house rules. Max 1900 chars. |
| project_description* | string |
Lint an AI agent context file (CLAUDE.md, .claude/rules/ files, AGENTS.md, Cursor rules, Copilot instructions, memory files) with PromptArch's deterministic linter: ~30 research-backed rule families covering current-model anti-patterns (tool-forcing, reasoning-echo, sycophancy triggers, contradictions), per-tool size budgets, secrets/dangerous commands, and hidden-Unicode injection ("Rules File Backdoor"). Returns grade, 0-100 score, and line-anchored findings. Free: no account or credits needed.
| Argument | Type | Description |
|---|---|---|
| format | string | Override format auto-detection. |
| content* | string | The full file content to lint. |
| filename | string | Filename hint for format detection (e.g. CLAUDE.md). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"content"
],
"properties": {
"format": {
"enum": [
"claude_md",
"claude_code_rule",
"agents_md",
"cursor_mdc",
"copilot_instructions",
"memory_file"
],
"type": "string",
"description": "Override format auto-detection."
},
"content": {
"type": "string",
"description": "The full file content to lint."
},
"filename": {
"type": "string",
"description": "Filename hint for format detection (e.g. CLAUDE.md)."
}
}
}List the artifact types promptarch_generate_artifact can produce from a project description.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"artifact",
"project_name",
"project_description"
],
"properties": {
"artifact": {
"enum": [
"context_pack",
"claude_md",
"agents_md",
"cursor_rule"
],
"type": "string",
"description": "Artifact id. See promptarch_list_artifact_types. Other Studio artifact types need artifact-specific inputs this tool does not accept."
},
"commands": {
"type": "string",
"maxLength": 1900
},
"tech_stack": {
"type": "string",
"maxLength": 1900
},
"project_name": {
"type": "string",
"maxLength": 1900
},
"target_model": {
"type": "string",
"maxLength": 100,
"description": "Target model family (default Claude)."
},
"repo_structure": {
"type": "string",
"maxLength": 1900,
"description": "Directory tree or structure summary. Max 1900 chars: summarize a large repo rather than pasting a full tree."
},
"coding_conventions": {
"type": "string",
"maxLength": 1900,
"description": "Conventions, invariants, house rules. Max 1900 chars."
},
"project_description": {
"type": "string",
"maxLength": 1900
}
}
}