add_blog · MCP Blog API MCP: Risk & Policy

WHAT IT DOES

What add_blog does on MCP Blog API

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

WHY IT NEEDS A POLICY

Why add_blog needs a policy

This tool creates new blog posts, which is a reversible modification operation. It does not delete, destroy, or execute arbitrary code—the user can remove or edit the post later. The severity is medium because a malicious agent could spam blogs or inject malicious content, but the impact is limited to blog data and remains reversible. Confidence is high because the intent is explicit in both name and description.

From the tool's definition Tool name 'add_blog' and description 'Add a new blog to the mock API' indicate creation of new data records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_blog Rate-limited

add_blog 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": {
    "add_blog": {
      "limits": [
        {
          "counter": "add_blog_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Blog API, so you can run agents against it safely.

FAQ

Questions about add_blog

What does the add_blog tool do? +

Add a new blog to the mock API. It is categorised as a Write tool in the MCP Blog API 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_blog? +

Register the MCP Blog API MCP server in PolicyLayer and add a rule for add_blog: 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 MCP Blog API. Nothing to install.

What risk level is add_blog? +

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

Can I rate-limit add_blog? +

Yes. Add a rate_limit block to the add_blog 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_blog completely? +

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

add_blog is provided by the MCP Blog API MCP server (tussanakorn/poc_mcp_protocol_using_fastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.