ScriptsMay 12, 2026·2 min read

MS-Agent — Lightweight Agent Framework with MCP

MS-Agent is a lightweight agent framework with MCP configs; install via pip and start with an LLMAgent example wired to Streamable HTTP MCP endpoints.

Agent Toolkit
Agent Toolkit · Community
Agent ready

Safe staging for this asset

This asset is staged first. The copied prompt tells the agent to inspect the staged files and ask before activating scripts, MCP config, or global config.

Stage only · 17/100Policy: stage
Agent surface
Any MCP/CLI agent
Kind
Mcp Config
Install
Stage only
Trust
Trust: Established
Entrypoint
Asset
Safe staging command
npx -y tokrepo@latest install 376e2fa5-a3f0-52fc-a8df-f212825e14a4 --target codex

Stages files first; activation requires review of the staged README and plan.

Intro

MS-Agent is a lightweight agent framework with MCP configs; install via pip and start with an LLMAgent example wired to Streamable HTTP MCP endpoints.

  • Best for: teams who want an agent runner that can consume MCP configs without building a custom harness
  • Works with: Python; ModelScope API (per README); Streamable HTTP MCP endpoints
  • Setup time: 15–35 minutes

Practical Notes

  • Quant: install is pip install ms-agent with an optional [research] extra per README.
  • Quant: validate MCP wiring by calling one tool via an MCP endpoint and logging the round-trip latency (baseline for regressions).

How to use it as a harness (not a demo)

The README example is a good start, but production usage needs guardrails:

  1. Pin MCP server configs per environment (dev/staging/prod) and store them in version control.
  2. Separate credentials from configs: env vars only, no secrets checked into repos.
  3. Replayability: keep a small set of “golden tasks” you can re-run after upgrades to detect regressions.

If your goal is evaluation/security, wrap runs with:

  • input/output logging,
  • tool-call allow-lists,
  • and a cost/latency budget per task.

FAQ

Q: Does it support MCP? A: Yes. The README includes an example mcpServers config wired into LLMAgent.

Q: How do I keep runs reproducible? A: Pin configs + keep golden tasks + log tool calls and outputs.

Q: What should I do first? A: Wire one simple MCP server endpoint and run a single task end-to-end before adding more tools.

🙏

Source & Thanks

Source: https://github.com/modelscope/ms-agent > License: Apache-2.0 > GitHub stars: 4,244 · forks: 496

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

mcp-use — Fullstack MCP Framework for AI Agents & Apps

Build MCP servers and apps for ChatGPT, Claude, and any LLM with TypeScript or Python SDK. Includes inspector, cloud deploy, and interactive widgets.

MCP ConfigsScripts
TokRepo精选

Feathers — Lightweight Real-Time API Framework for Node.js

Feathers is a lightweight web framework for building real-time applications and REST APIs with Node.js. It provides a service-oriented architecture that works with Express, Koa, or its own HTTP transport.

Skills
Script Depot

CAMEL — Multi-Agent Framework at Scale

CAMEL is a multi-agent framework for studying scaling laws of AI agents. 16.6K+ GitHub stars. Up to 1M agents, RAG, memory systems, data generation. Apache 2.0.

Skills
Script Depot

Oh My Codex — Multi-Agent Orchestration for AI Coding

Add hooks, agent teams, HUDs, and collaborative workflows to Codex and other AI coding tools with a lightweight orchestration layer.

Scripts
Script Depot
◈Home🔍Search👤Me