github_init_and_push

A write tool on the Github MCP server.

SERVERGithub SOURCEdkeeno/github-mcp-server

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/dkeeno-github-mcp-server/github-init-and-push.md

WHAT IT DOES

What github_init_and_push does on Github

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

RISK

Why github_init_and_push is rated Medium

The tool initializes and pushes to GitHub, which creates new repositories or modifies existing ones—a reversible write operation. While the description is empty, the name and server context strongly indicate repository creation/modification. This is Write rather than Execute because it's a high-level Git operation that modifies data rather than executing arbitrary commands.

From the tool's definition Tool name 'github_init_and_push' combined with server description indicating 'push' and 'portfolio push tool to create repos from local folders' suggests creating repositories and pushing code.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

github_init_and_push Rate-limited

github_init_and_push 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": {
    "github_init_and_push": {
      "limits": [
        {
          "counter": "github_init_and_push_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 Github, apply this rule, and every github_init_and_push call is checked against it from then on.

FAQ

Questions about github_init_and_push

What does the github_init_and_push tool do? +

github_init_and_push is a write tool on the Github MCP server. It is categorised as a Write tool in the Github MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on github_init_and_push? +

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

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

Can I rate-limit github_init_and_push? +

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

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

github_init_and_push is provided by the Github MCP server (dkeeno/github-mcp-server). 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 69 Github tools →

Across the catalogue

generate_and_fetch_code on Stitch MCP Server → The MCP Attack Database →

Guides

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