Developer · Local MCP server
Promptheus
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.abhichandra21/promptheus- Version
- 0.3.1
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2025-12-10
- Updated
- 2025-12-10
- Publisher
- abhichandra21 (GitHub)
- Website
- github.com/abhichandra21/Promptheus
- Repository
- github.com/abhichandra21/Promptheus.git
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: python | promptheus | 0.3.1 | stdio |
How to connect Promptheus
Promptheus runs locally from a Python package published to PyPI: promptheus version 0.3.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx promptheus; the entry names python as the runtime. It reads these environment variables: GOOGLE_API_KEY (secret), ANTHROPIC_API_KEY (secret), OPENAI_API_KEY (secret), GROQ_API_KEY (secret), QWEN_API_KEY (secret), GLM_API_KEY (secret), PROMPTHEUS_PROVIDER and PROMPTHEUS_MODEL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"promptheus": {
"command": "uvx",
"args": [
"promptheus"
],
"env": {
"GOOGLE_API_KEY": "<secret>",
"ANTHROPIC_API_KEY": "<secret>",
"OPENAI_API_KEY": "<secret>",
"GROQ_API_KEY": "<secret>",
"QWEN_API_KEY": "<secret>",
"GLM_API_KEY": "<secret>",
"PROMPTHEUS_PROVIDER": "<value>",
"PROMPTHEUS_MODEL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Promptbudget MCPToken-budget-aware text handling: count, truncate, and chunk for LLM prompts. | Local · stdio |
| PromptEdenStdio MCP server for PromptEden projects, monitors, answers, and analytics. | Local · stdio |
| PromptGuardScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client. | Local · stdio |
| PromptGuard Scan MCPPaid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness. | Remote · HTTP |
| Promptlike MCPYour PromptLikeEngineer prompt library as MCP tools, slash prompts and resources. Add-only saves. | Local · stdio |
| Promptlint MCPStatic linter for AI prompts: contradictions, redundancy, ambiguity, and fluff. | Local · stdio |
| PromptOTManage, version, and publish LLM prompts with blocks, variables, and evaluations. | Remote & Local · HTTP, stdio |
| PromptrejectormcpSecurity gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities. | Local · stdio |