Promptheus runs on your own machine — the client starts it, so there is no endpoint to ping. 89 installs a week from pypi. Last commit 6 Feb 2026.
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
Today is the operative word: we check Promptheus every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add promptheus -- uvx promptheus
{
"mcpServers": {
"promptheus": {
"args": [
"promptheus"
],
"command": "uvx"
}
}
}
[mcp_servers.promptheus]
command = "uvx"
args = ["promptheus"]
{
"mcpServers": {
"promptheus": {
"args": [
"promptheus"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"promptheus": {
"args": [
"promptheus"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
GOOGLE_API_KEY (Google Gemini API key (optional, at least one provider required)), ANTHROPIC_API_KEY (Anthropic Claude API key (optional, at least one provider required)), OPENAI_API_KEY (OpenAI API key (optional, at least one provider required)), GROQ_API_KEY (Groq API key (optional, at least one provider required)), QWEN_API_KEY (Alibaba Qwen API key (optional, at least one provider required)), GLM_API_KEY (Zhipu GLM API key (optional, at least one provider required)), PROMPTHEUS_PROVIDER (Override provider selection (gemini, anthropic, openai, groq, qwen, glm)), PROMPTHEUS_MODEL (Override model selection for the chosen provider).
The author declared them in the registry entry; get the values from the project itself.
Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
RMCP runtime for provider-backed agents with CLI, REST, HTTP MCP, plugins, and scaffold support.
Local Chrome via CDP with profile-snapshot isolation and shared-broker multi-client support
Self-improving AI workflows with backtesting, prompt optimization, and scheduling
Multi-provider AI router with x402 micropayment settlement on Base L2. 1% flat fee.
AI-powered survey builder ai MCP server for agents. Supports create survey, validate questions
AI-powered project analysis with risk identification, forecasting, and mitigation generation
Answers built from our own checks of this server.