// SCAN REPORT

Rocket Plus

106 tools. 38 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Jun 2026

38 can modify or destroy data

68 read-only

106 tools total

Free to start. No card required.

TOOL MAP

Read (68) Write / Execute (37) Destructive / Financial (1)

CONTEXT-WINDOW COST

7,408 tokens of tool definitions, loaded on every request

3.7% of a 200k context window

201 heaviest tool: recurring_tasks_create

Full per-tool breakdown → Model it in the token calculator →

WHAT CAN GO WRONG

Destructive tools (recurring_tasks_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (add_tags, apex_create_test, canvas_create) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (agent_execute, gcloud_functions_invoke, recurring_tasks_run_now) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "recurring_tasks_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_tags": {
    "limits": [
      {
        "counter": "add_tags_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agent_list": {
    "limits": [
      {
        "counter": "agent_list_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

ALL 106 ROCKET PLUS TOOLS

DESTRUCTIVE 1 tools

Destructive recurring_tasks_delete

EXECUTE 4 tools

Execute agent_execute Execute gcloud_functions_invoke Execute recurring_tasks_run_now Execute rocketflow_deploy

READ 68 tools

Read agent_list Read agent_status Read apex_get_results Read apex_optimize Read api_list_endpoints Read api_test Read content_ideas Read content_rewrite Read course_outline Read cro_analyze Read cro_heatmap Read focus_get_tasks Read form_get_submissions Read game_stats Read gcloud_apis_list Read gcloud_bigquery_datasets Read gcloud_bigquery_query Read gcloud_functions_list Read gcloud_iam_service_accounts Read gcloud_projects_list Read gcloud_status Read gcloud_storage_buckets Read gcloud_storage_list Read get_contacts Read get_location_stats Read get_opportunities Read get_usage Read google_calendar_events Read google_calendar_freebusy Read google_calendar_list Read google_drive_list Read google_drive_search Read google_gmail_labels Read google_gmail_search Read google_sheets_append Read google_sheets_read Read google_tasks_get Read google_tasks_status Read google_workspace_status Read insights_analyze Read insights_predict Read insights_report Read list_mods Read mcp_call_server Read mcp_list_servers Read pdl_auto_enrich_contact Read pdl_enrich_company Read pdl_enrich_person Read pdl_search_companies Read pdl_search_people Read recurring_tasks_history Read recurring_tasks_list Read research_competitors Read research_ideas Read research_trends Read rocketflow_templates Read rocketflow_validate Read rss_get_items Read seo_analyze Read seo_keyword_research Read tasks_analyze Read tasks_get_lists Read tasks_sync_ghl Read tasks_sync_google Read tasks_sync_sheets Read visitors_active Read visitors_history Read webhook_list

FAQ

Can an AI agent delete data through the Rocket Plus MCP server? +

Yes. The Rocket Plus server exposes 1 destructive tools including recurring_tasks_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Rocket Plus? +

The Rocket Plus server has 33 write tools including add_tags, apex_create_test, canvas_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Rocket Plus.

How many tools does the Rocket Plus MCP server expose? +

106 tools across 4 categories: Destructive, Execute, Read, Write. 68 are read-only. 38 can modify, create, or delete data.

How do I enforce a policy on Rocket Plus? +

Register the Rocket Plus MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Rocket Plus tool call.

Deterministic rules across all 106 Rocket Plus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE ROCKET PLUS →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Rocket Plus

// TOOL MAP

// CONTEXT-WINDOW COST

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 106 ROCKET PLUS TOOLS

// FAQ