MCPInstall
Directory

MCP servers

13 servers that let your AI assistant read data and take actions in the tools you use.

13 results“Evaluate”

Used Archon to create financial ai agents that cooperate with the stock server MCP to evaluate potential investment risks

CreateEvaluate+3

Query a list of running Drivers and evaluate the output

OutputQuery+3

Mimic-mcp-server evaluates MCP Server on PostgreSQL for efficient clinical analytics.

CLIAnalytics+1

mcp_vs_mdp_explained

janMagnusHeimann

This document contrasts Markov Reward Processes (MRPs) and Markov Decision Processes (MDPs) in Reinforcement Learning. MRPs model states and rewards (no actions) to evaluate state values (V(s)) via the Bellman equation. MDPs add actions and policies (π) to find optimal strategies (V ∗ ,Q ∗ ) using Bellman optimality equations.

DocumentModel+8

any-agent

mozilla-ai

A single interface to use and evaluate different agent frameworks

DiffEvaluate+1

opik

comet-ml

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

DashboardWorkflow+3

MAGI Code Review

miki-hoshizaki

Orchestrates code reviews through a distributed framework of three specialized agents (Melchior, Balthasar, and Casper) that evaluate submissions and deliver majority-rule verdicts on code quality.

Developer Tools

mcp-te-benchmark

twilio-labs

A framework to evaluate AI agents' efficiency using Model Context Protocol.

TextModel+1

web-qa-agent

Operative-Sh

An MCP server that evaluates web applications.

WebEvaluate

web-agent-qa

Operative-Sh

An MCP server that evaluates web applications.

WebEvaluate

AWorld

inclusionAI

Build, evaluate and run General Multi-Agent Assistance with ease

RunEvaluate

web-eval-agent

Operative-Sh

An MCP server that evaluates web applications.

WebEvaluate

Integrates with Google Maps to locate and evaluate medical facilities in emergencies, providing tools for facility search, route calculation, and availability checking within a 10km radius, while implementing sequential thinking for step-by-step clinical reasoning and accurate facility matching based on patient data.

datasearch+1