ModelsAtlas
Explore
Atlas / MCP servers / sam-92 / AutoGen SSE Stdio

AutoGen SSE StdioSAFE

mcp/sam-92/autogen-sse-stdio
MCP server by sam-92 · ai · autogen · azure · Audited 2026-10-08
⚑ Report / re-scanSource ↗

This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 1r · 1w · 0d
Transport
stdio
License
—
Stars
29
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

This repository provides a practical demonstration of integrating tools with AI agents using the Model Context Protocol (MCP) within the AutoGen framework.

Key Features Demonstrated:

  • Dual MCP Integration: Shows how to connect an AutoGen agent to:
  • A local tool server (math_server.py) using Stdio transport.
  • A remote tool server (Apify's RAG Web Browser Actor) using Server-Sent Events (SSE) transport.
  • Local Tool Example: A simple calculator (add, multiply) running locally via math_server.py.
  • Remote Tool Example: Leveraging Apify's RAG Web Browser Actor via their MCP Server for web searching and content retrieval.
  • AutoGen Agent: An AssistantAgent configured to utilize both sets of tools to answer user queries.

Goal: To illustrate the flexibility of MCP in enabling AI agents to access diverse tools, whether hosted locally or remotely, through standardized communication protocols (Stdio and SSE).

Scenario: The example agent answers two distinct questions:

  1. A math problem ((3 + 5) x 12?), expected to use the local math_server.py.
  2. A request for recent news ("Summarise the latest news of Iran and US negotiations..."), expected to use the remote Apify web browsing tool.

📚 Libraries & Frameworks Used

  • AutoGen: AI agent framework (autogenagentchat, autogencore, autogen_ext)
  • MCP: Model Context Protocol for tool integration
  • Python-dotenv: For environment variable management
  • OpenAI API: For LLM capabilities
  • Apify API: For web browsing capabilities

🛠️ Setup

Follow these steps carefully to set up your environment:

  1. Prerequisites:
  • Ensure you have Python 3.12 installed.
  • Install uv if not already installed:
pip install uv
  1. **Navigate to P
Read from source at commit 4f343eb16094OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-server-examples --env APIFY_API_KEY=${APIFY_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp-server-examples
claude-desktop
{
  "mcpServers": {
    "mcp-server-examples": {
      "command": "uvx",
      "args": [
        "mcp-server-examples"
      ],
      "env": {
        "APIFY_API_KEY": "${APIFY_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
03

Exposed tools (2)

1 read · 1 write · 0 destructive.

ToolRiskDescription
addwriteAdd two numbers
multiplyreadMultiply two numbers
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (3)

MEDIUMInventory / provenance · inv.binary · CWE-1104
.DS_Store
.DS_Store
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWInventory / provenance · inv.hidden_file · CWE-1104
.DS_Store
.DS_Store
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f343eb16094full audit observations/trust-audit/mcp-server/sam-92__autogen-sse-stdio.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-084f343eb16094SAFEB89first audit
06

Questions

What is the AutoGen SSE Stdio MCP server?

This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.

What tools does AutoGen SSE Stdio expose?

2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is AutoGen SSE Stdio safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does AutoGen SSE Stdio need?

It reads APIFY_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does AutoGen SSE Stdio run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server-examples.

How current is this page?

The grade is for one exact copy of the source (4f343eb16094), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement