meta_debug_token

THE RISK

Low Risk

Why meta_debug_token needs a policy

This tool retrieves and displays information about an existing access token (its type, expiry, permissions, app/user association). It performs no modifications, deletions, or external operations. While token inspection could theoretically expose sensitive information, the action itself is a passive read operation.

From the tool's definition Tool name 'meta_debug_token' and description: 'Inspects the current Meta access token to show its type, expiry, permissions, and associated app/user.' The verb 'inspects' and 'show' indicate read-only retrieval of token metadata with no side effects.

Documented attack patterns abuse exactly the kind of access meta_debug_token gives an agent:

POLICY

How to control meta_debug_token

PolicyLayer is an MCP gateway — it sits between your AI agents and Meta MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for meta_debug_token:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "meta_debug_token": {}
  }
}

meta_debug_token is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Meta MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Meta MCP Server tools

Financial meta_create_adset Creates a new ad set within a campaign. Args: - ad_account_id (string): Ad account ID ( Financial meta_create_campaign Creates a new campaign in a Meta ad account. Args: - ad_account_id (string): Ad account Destructive meta_delete_ad Deletes an ad permanently. Args: - ad_id (string): Ad ID to delete Destructive meta_delete_ad_rule Deletes an automated ad rule. Args: - rule_id (string): Ad rule ID Destructive meta_delete_adset Deletes an ad set permanently. Args: - adset_id (string): Ad set ID to delete Destructive meta_delete_campaign Deletes (archives) a campaign. This cannot be undone. Args: - campaign_id (string): Cam Destructive meta_delete_comment Deletes a comment on a Facebook Page post. Permanent action. Args: - comment_id (string Destructive meta_delete_custom_audience Deletes a custom audience permanently. This cannot be undone. Args: - audience_id (stri

All 200 Meta MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about meta_debug_token

What does the meta_debug_token tool do? +

Inspects the current Meta access token to show its type, expiry, permissions, and associated app/user. Useful for diagnosing. It is categorised as a Read tool in the Meta MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on meta_debug_token? +

Register the Meta MCP Server MCP server in PolicyLayer and add a rule for meta_debug_token: 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 Meta MCP Server. Nothing to install.

What risk level is meta_debug_token? +

meta_debug_token is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit meta_debug_token? +

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

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

meta_debug_token is provided by the Meta MCP Server MCP server (oliverames/meta-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Meta MCP Server tool call.

Start from Meta MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →