output

Shows Terraform output values from the current state. Returns structured name/value/type/sensitive data.

SERVERGithub SOURCE@paretools/github

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-github/output.md

WHAT IT DOES

What output does on Github

AI agents call output to retrieve information from Github without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why output is rated Low

This tool performs a read-only query operation that retrieves Terraform output values. It returns data (name/value/type/sensitive flags) from the current state without side effects. While the server is described as a GitHub operations tool, this particular tool appears to be a Terraform utility for displaying outputs.

From the tool's definition The tool 'Shows Terraform output values from the current state. Returns structured name/value/type/sensitive data.' retrieves and queries existing Terraform state outputs without modifying, deleting, or executing anything.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs output safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For output, this is the rule to start with:

output Allowed

output is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "output": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every output call is checked against it from then on.

FAQ

Questions about output

What does the output tool do? +

Shows Terraform output values from the current state. Returns structured name/value/type/sensitive data. It is categorised as a Read tool in the Github MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on output? +

Register the Github MCP server in PolicyLayer and add a rule for output: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Github. Nothing to install.

What risk level is output? +

output is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit output? +

Yes. Add a rate_limit block to the output rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block output completely? +

Set action: deny in the PolicyLayer policy for output. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides output? +

output is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Github, and thousands of servers like it.

This server

All 202 Github tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →