pull

Pulls a Docker image from a registry and returns structured result with digest info.

SERVERGithub SOURCE@paretools/github

High RISK CLASS

Category Execute

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-github/pull.md

WHAT IT DOES

What pull does on Github

AI agents invoke pull to trigger actions in Github. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why pull is rated High

Pulling a Docker image is an external operation that fetches data from a remote registry and stores it on the local system. It is not a pure read (has side effects: disk write, local image store modification), not destructive, not financial. Execute is the best fit as it triggers an external operation with side effects dependent on the argument (image name/tag).

From the tool's definition 'Pulls a Docker image from a registry' — triggers an external operation (network pull) that downloads and stores an image locally

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pull 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 pull, this is the rule to start with:

pull Rate-limited

pull stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pull": {
      "limits": [
        {
          "counter": "pull_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about pull

What does the pull tool do? +

Pulls a Docker image from a registry and returns structured result with digest info. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pull? +

Register the Github MCP server in PolicyLayer and add a rule for pull: 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 pull? +

pull is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pull? +

Yes. Add a rate_limit block to the pull 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 pull completely? +

Set action: deny in the PolicyLayer policy for pull. 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 pull? +

pull 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 → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →