Submit a Meta or Google Ads write action (validated by API, executed by n8n). Token needs ads:write or ads:admin. provider: meta|google must match action_type prefix. action_type must be one of: meta.status.v1, meta.budget.v1, meta.bid.v1, meta.creative.v1, meta.targeting.v1, meta.lifecycle.v1, g...
Accepts raw HTML/template content (payload); Admin/system-level operation
Part of the Gsquad MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use gsquad_ads_action_submit to create or modify resources in Gsquad. 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 gsquad_ads_action_submit repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Gsquad.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
gsquad_ads_action_submit:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Gsquad policy for all 10 tools.
Agents calling write-class tools like gsquad_ads_action_submit have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Submit a Meta or Google Ads write action (validated by API, executed by n8n). Token needs ads:write or ads:admin. provider: meta|google must match action_type prefix. action_type must be one of: meta.status.v1, meta.budget.v1, meta.bid.v1, meta.creative.v1, meta.targeting.v1, meta.lifecycle.v1, google.status.v1, google.budget.v1, google.bid.v1, google.creative.v1, google.targeting.v1, google.lifecycle.v1. payload must include required keys per action_type: meta/google *.status.v1 → object_id|resource_name + status; *.budget.v1 → + budget_spec; *.bid.v1 → + bid_spec; *.creative.v1 → + creative_spec; *.targeting.v1 → + targeting_spec; *.lifecycle.v1 → operation + spec. Use dry_run:true to validate without dispatching. idempotency_key avoids duplicate runs per user. For *.lifecycle.v1 non-dry-run, set confirm to ADS_CRITICAL_CONFIRM_TOKEN value. Poll gsquad_ads_action_status with returned public_id. See package README (Ads actions section) for examples.. It is categorised as a Write tool in the Gsquad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for gsquad_ads_action_submit. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Gsquad MCP server.
gsquad_ads_action_submit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gsquad_ads_action_submit rule in your Intercept 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.
Set action: deny in the Intercept policy for gsquad_ads_action_submit. 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.
gsquad_ads_action_submit is provided by the Gsquad MCP server (gsquad-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.