socheli_publish · Socheli MCP: Risk & Policy

WHAT IT DOES

What socheli_publish does on Socheli

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

WHY IT NEEDS A POLICY

Why socheli_publish needs a policy

This tool creates new published content across multiple social media platforms, which is a Write operation (content creation/modification with side effects). Severity is high because publishing to major platforms affects broad audiences and could spread misinformation, inappropriate content, or violate platform policies if misused by an AI agent.

From the tool's definition Tool description states 'Publish a finished item to every configured platform (YouTube/IG/TikTok + bundle). Set public to go public.' - this creates or modifies content visibility across multiple external platforms irreversibly in practical terms.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

socheli_publish Rate-limited

socheli_publish 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": {
    "socheli_publish": {
      "limits": [
        {
          "counter": "socheli_publish_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 Socheli, so you can run agents against it safely.

FAQ

Questions about socheli_publish

What does the socheli_publish tool do? +

Publish a finished item to every configured platform (YouTube/IG/TikTok + bundle). Set public to go public. It is categorised as a Write tool in the Socheli MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on socheli_publish? +

Register the Socheli MCP server in PolicyLayer and add a rule for socheli_publish: 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 Socheli. Nothing to install.

What risk level is socheli_publish? +

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

Can I rate-limit socheli_publish? +

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

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

socheli_publish is provided by the Socheli MCP server (socheli/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.