variable-set

Sets a repository, organization, or environment GitHub Actions variable. Variables are not secret and may be visible in logs.

SERVERBuild SOURCEDave-London/Pare

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-build/variable-set.md

WHAT IT DOES

What variable-set does on Build

AI agents use variable-set to create or update resources in Build, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Build environment.

RISK

Why variable-set is rated Medium

This tool modifies GitHub Actions configuration by setting environment variables at repository, organization, or environment scope. While not irreversible (variables can be updated or deleted), it creates or modifies infrastructure state that affects CI/CD pipelines and application behavior.

From the tool's definition Tool description states it 'Sets a repository, organization, or environment GitHub Actions variable', which is a create/modify operation. The note that 'Variables are not secret and may be visible in logs' indicates persistence and visibility.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs variable-set safely

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

variable-set Rate-limited

variable-set stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "variable-set": {
      "limits": [
        {
          "counter": "variable-set_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about variable-set

What does the variable-set tool do? +

Sets a repository, organization, or environment GitHub Actions variable. Variables are not secret and may be visible in logs. It is categorised as a Write tool in the Build MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on variable-set? +

Register the Build MCP server in PolicyLayer and add a rule for variable-set: 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 Build. Nothing to install.

What risk level is variable-set? +

variable-set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit variable-set? +

Yes. Add a rate_limit block to the variable-set 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 variable-set completely? +

Set action: deny in the PolicyLayer policy for variable-set. 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 variable-set? +

variable-set is provided by the Build MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Build, and thousands of servers like it.

This server

All 202 Build tools →

Across the catalogue

set-prioity on Kanban MCP Server →team_manager_set_sources on Team Manager MCP →qt_set_property on Qt → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →