zscaler
zscaler/zscaler-mcp-serverPlugin
Manage Zscaler cloud security platform including ZPA (private access), ZIA (internet access), ZDX (digital experience), ZCC (client connector), EASM (attack surface), and Z-Insights (analytics). Create and manage policies, troubleshoot connectivity, audit security configurations, and investigate incidents across the full Zscaler ecosystem.
Why this score
Popularity score: 69/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Nov 4, 2026 at commit 6340cd24087a, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.
What its code does:
- Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.src/zscaler_mcp/security/auth.py, src/zscaler_mcp/server.py and 2 more
- Runs shell commands Common for dev tools. Read the commands it runs.README.md:1, integrations/aws/bedrock-agentcore/strands_agent_chat.py:1032, integrations/azure/foundry_agent.py:928 and 2 more
- Makes network requestsintegrations/aws/bedrock-agentcore/aws_mcp_operations.py:339, integrations/aws/bedrock-agentcore/cloudformation/lambda/gateway_provisioner.py:80, integrations/aws/bedrock-agentcore/cloudformation/lambda/runtime_provisioner.py:64 and 23 more
- Installs system packagesintegrations/aws/ec2/ec2_mcp_operations.py:2022
- Uses dependencies without a pinned version A later version of a dependency could change what runs.pyproject.toml:26 and 24 more
Web addresses in its code:
- docs.aws.amazon.comintegrations/aws/bedrock-agentcore/aws_mcp_operations.py:799
- ai.azure.comintegrations/azure/foundry_agent.py:34
- aws.amazon.comintegrations/aws/bedrock-agentcore/aws_mcp_operations.py:1497
- s3.amazonaws.comintegrations/aws/ec2/ec2_mcp_operations.py:2019
- cloud.google.comintegrations/google/adk/adk_agent_operations.py:443
- kubernetes.iointegrations/aws/eks/eks_mcp_operations.py:1760
- zscaler.comsrc/zscaler_mcp/common/mcpb.py:128
- aka.msintegrations/azure/azure_mcp_operations.py:3001
- api.github.comsrc/zscaler_mcp/lifecycle.py:683
- api.zscaler.comsrc/zscaler_mcp/security/auth.py:150
- app.box.comsrc/zscaler_mcp/tools/zia/url_categories.py:226
- discoveryengine.googleapis.comintegrations/google/adk/adk_agent_operations.py:736
- docs.docker.comscripts/setup-mcp-server.py:783
- docs.python.orgdocsrc/conf.py:195
- graph.microsoft.comintegrations/aws/bedrock-agentcore/cloudformation/lambda/gateway_provisioner.py:424
And 7 more.
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Nothing from another maker does quite the same job yet.