Medium Risk

create_pr

Create a new branch (git ref), one commit from the base tree with your file changes, then open a pull request in the same repository. REQUIRES: Github-Token (HTTP) or GITHUB_TOKEN with contents: write (and no existing branch with the same headBranch name).

Risk signalsAccepts raw HTML/template content (body) · Accepts file system path (files[].path) · High parameter count (11 properties)

Part of the Mermaid Mcp server.

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

SECURE MERMAID MCP →

Free to start. No card required.

AI agents use create_pr to create or modify resources in Mermaid Mcp. 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 create_pr 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 Mermaid Mcp.

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

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

See the full Mermaid Mcp policy for all 17 tools.

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

ENFORCE ON MY MERMAID MCP →

View all 17 tools →

These attack patterns abuse exactly the kind of access create_pr 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 create_pr only ever does what you allow.

SECURE MERMAID MCP →

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

What does the create_pr tool do? +

Create a new branch (git ref), one commit from the base tree with your file changes, then open a pull request in the same repository. REQUIRES: Github-Token (HTTP) or GITHUB_TOKEN with contents: write (and no existing branch with the same headBranch name).. It is categorised as a Write tool in the Mermaid Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_pr? +

Register the Mermaid MCP server in PolicyLayer and add a rule for create_pr: 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 Mermaid Mcp. Nothing to install.

What risk level is create_pr? +

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

Can I rate-limit create_pr? +

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

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

create_pr is provided by the Mermaid MCP server (https://mcp.mermaidchart.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mermaid Mcp tool call.

Deterministic rules across all 17 Mermaid Mcp 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.