Skip to main content
The Model Context Protocol (MCP) and Open Reward Standard (ORS) are both protocols for connecting language models to external systems, but they serve different purposes.

​
Overview

Model Context Protocol (MCP):
  • Purpose: Connect LLMs to tools, data sources, and workflows
  • Focus: General-purpose tool access
  • Use case: Extending LLM capabilities with external APIs, databases, file systems
Open Reward Standard (ORS):
  • Purpose: Connect agents to reinforcement learning environments
  • Focus: RL training and agent evaluation
  • Use case: Training agents with reward signals, structured evaluation benchmarks

​
Key Differences

FeatureMCPORS
Primary PurposeTool access, data integrationRL training environments
Episode TerminationNo conceptfinished signal
RewardsNo conceptNumeric feedback for RL
TasksNo conceptOrganised problems to solve
SplitsNo conceptTasks organised into splits
Session ManagementBasicEpisode-centric (RL trajectories)
Tool CallingYesYes Yes
ProtocolJSON-RPC over stdio/SSEHTTP/REST + SSE

​
Detailed Comparison

​
Tool Calling

Both protocols support tool calling with similar interfaces: MCP Tool Spec: 
{
  "name": "read_file",
  "description": "Read contents of a file",
  "inputSchema": {
    "type": "object",
    "properties": {
      "path": {"type": "string"}
    }
  }
}
ORS Tool Spec: 
{
  "name": "read_file",
  "description": "Read contents of a file",
  "input_schema": {
    "type": "object",
    "properties": {
      "path": {"type": "string"}
    }
  }
}
ORS intentionally aligns with MCP’s tool specification format.

​
Tool Responses

MCP Response: 
{
  "content": [
    {"type": "text", "text": "File contents here"}
  ]
}
ORS Response: 
{
  "blocks": [
    {"type": "text", "text": "File contents here"}
  ],
  "reward": 0.0,
  "finished": false
}
ORS adds:
  • reward - For RL training feedback
  • finished - For episode termination

​
Episode Structure

MCP: No concept of episodes. Stateless or loosely stateful tool calls. ORS: Episodes are first-class:
  • Session = RL episode
  • Episode continues until finished: true
  • One complete trajectory through environment
  • Clear start (task) and end (finished signal)

​
Task Organization

MCP: No built-in task organization. ORS: Tasks and splits:
  • Tasks: Individual problems to solve
  • Splits: tasks grouped into splits, e.g. train/val/test

​
Next Steps

ORS Quick Start

Build your first ORS server

ORS Specification

Deep dive into ORS protocol

MCP Documentation

Learn about Model Context Protocol

Implementation Guide

Implement an ORS server
Key Takeaway: MCP and ORS solve different problems. MCP connects LLMs to tools. ORS connects agents to RL training environments. Both are valuable, and they can work together in sophisticated systems.