Medium Risk

add

Stages files for commit. Returns structured data with count and list of staged files, including how many were newly staged. Pass path to target a specific repo or worktree — when omitted, operates on the server's own working directory, not the caller's (see #876).

Risk signalsAccepts file system path (path) · High parameter count (12 properties)

Part of the Github server.

add can modify Github data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE GITHUB →

Free to start. No card required.

AI agents use add to create or modify resources in Github. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call add repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Github.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add": {
      "limits": [
        {
          "counter": "add_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Github policy for all 28 tools.

Get this rule live on your own Github server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY GITHUB →

View all 28 tools →

These attack patterns abuse exactly the kind of access add gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so add only ever does what you allow.

SECURE GITHUB →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the add tool do? +

Stages files for commit. Returns structured data with count and list of staged files, including how many were newly staged. Pass path to target a specific repo or worktree — when omitted, operates on the server's own working directory, not the caller's (see #876).. 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 add? +

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

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

Can I rate-limit add? +

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

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

add 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.

Enforce policy on every Github tool call.

Deterministic rules across all 28 Github tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.