Home/AI Agents/mcp-agent

mcp-agent

lastmile-ai/mcp-agent

Build effective AI agents with Model Context Protocol.

GitHub

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

52views this month

8.5k stars891 forksLast push Jan 25, 2026 Python Apache-2.0

Decision brief

Allows creation of efficient AI agents via Model Context Protocol with workflow patterns

Good fit when

Need to implement the Model Context Protocol specifically in your agent development
Prefer tools that offer straightforward integration of predefined workflow patterns

Avoid when

Require a more customizable approach beyond pre-defined protocol and workflows
Project demands specific AI frameworks unsupported by Model Context Protocol directly

Observed Jul 16, 2026 · Source: enrich:decision_facts

mcp-agent alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (237d since push); As of Sep 20, 2026
Provenance: Not a fork · Organization account; As of Sep 20, 2026
Security (OSV): No MCP manifest; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install mcp-agent

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

ai-agents-for-beginners

12 Lessons to Get Started Building AI Agents

75k★

agentscope

Build and run agents you can see, understand and trust.

32k★

openai-agents-python

A lightweight, powerful framework for multi-agent workflows

30k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Offers tools for creating efficient AI agents using the Model Context Protocol and workflow patterns.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 20, 2026
Languages: python
Source: github.language+pyproject.toml · Sep 20, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Sep 20, 2026)

We recommend using [uv](https://docs.astral.sh/uv/) to manage your Python projects (`uv init`).

Source link

README

The Getting Started guide walks through configuration and secrets in detail. bash uv add "mcp agent" bash pip install mcp agent bash uvx mcp agent login uvx mcp agent deploy my agent uvx mcp agent cloud apps list `` examples/cloud`](./examples/cloud/).

For agents

This page has a .md twin and JSON over the API.

/tools/lastmile-ai-mcp-agent.md GET /api/graphcanon/tools/lastmile-ai-mcp-agent GET /api/graphcanon/graph?tool=lastmile-ai-mcp-agent