github.com/pagerduty/github-agenthq-plugins · main · scanned 2 h ago · 1 config file

1 agent component (1 MCP server), declared 2 times in pagerduty/github-agenthq-plugins: 1 credential handed to agents.

Components11 MCP server
High blast radius0credentials, shell or unvetted code
Credentials handed to agents1Authorization
Not vetted0of 0 local servers, skills and plugins · 1 hosted
ComponentWhereVerdictBlast radius
pagerdutyMCP server · Claude Code · httpmcp.pagerduty.com
.mcp.jsonhosted · no package
medium
  • is handed a credential: Authorization
  • sends the agent's tool calls and their data to mcp.pagerduty.com
  • is not a registry package, so there is no verdict to check
Authorization
pagerduty-advanceMCP server · Claude Code · httpmcp.pagerduty.com
.mcp.jsonhosted · no package
medium
  • is handed a credential: Authorization
  • sends the agent's tool calls and their data to mcp.pagerduty.com
  • is not a registry package, so there is no verdict to check
Authorization
What to do about it
  • Each credential listed is readable by the server it is given to. Scope keys to what that server needs, and prefer servers with a Verified verdict for anything holding cloud or payment keys.
  • Hosted servers have no package to run in the sandbox. Everything the agent sends them goes to that host, so treat the credential as the trust decision. Teams can watch a hosted server's tool list for changes.
  • For a whole organization (every repo and laptop, rescanned daily, with removal across machines), see Discovery for teams.
Share: https://killerskills.ai/scan/github/pagerduty/github-agenthq-pluginsRescan nowScan another