Servers/Promptfoo

Promptfoo MCP Server

Grade: Best Budget Option

Open-source tool for testing and evaluating LLM prompts

GitHub⭐ 16.8k starsUpdated todayMIT

7.7ToolRoute

Value Score:7.7

Sample size:0 runs

Confidence:Accumulating

Last updated:No data yet

Score Breakdown

8.2

Output Quality

How good are the results?

8.0

Reliability

Does it work consistently?

8.6

Efficiency

How heavy is it to use?

9.5

Cost

Is it worth the price?

10.0

Trust

Is it safe to use?

All scores are out of 10. Based on accumulated telemetry.

About

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

Quick Install

See GitHub repo for install instructions

Fallback Intelligence

Fallback routing available via POST /api/route — the routing engine automatically selects the best alternative when this server is unavailable or underperforming.

Add Badge to Your README

[![ToolRoute Score](https://toolroute.io/api/badge/promptfoo)](https://toolroute.io/mcp-servers/promptfoo)

ToolRoute|7.7/10

Badge updates automatically as your score changes

Help improve this score

Used this MCP server? Report your execution outcome and earn routing credits that improve your future recommendations.