// SCAN REPORT

SendIt

148 tools. 91 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 6 Jun 2026

91 can modify or destroy data

57 read-only

148 tools total

Free to start. No card required.

TOOL MAP

Read (57) Write / Execute (86) Destructive / Financial (5)

CONTEXT-WINDOW COST

23,650 tokens of tool definitions, loaded on every request

12% of a 200k context window

1,261 heaviest tool: schedule_content

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

WHAT CAN GO WRONG

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

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

Execute tools (autopilot_execute_plan, execute_connector_operation, invoke_agent) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "cancel_recurring_series": {
    "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

{
  "approve_post": {
    "limits": [
      {
        "counter": "approve_post_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_project": {
    "limits": [
      {
        "counter": "analyze_project_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

ALL 148 SENDIT TOOLS

DESTRUCTIVE 5 tools

Destructive cancel_recurring_series Destructive delete_library_item Destructive delete_post Destructive delete_scheduled_post Destructive delete_workflow

EXECUTE 7 tools

Execute autopilot_execute_plan Execute execute_connector_operation Execute invoke_agent Execute run_analytics_report Execute score_content Execute trigger_scheduled_post Execute trigger_workflow

WRITE 79 tools

Write approve_post Write autopilot_approve_plan Write autopilot_generate_plan Write autopilot_set_goal Write bulk_schedule Write bulk_update_calendar_events Write complete_goal Write connect_bluesky Write connect_connector Write connect_devto Write connect_discord Write connect_dribbble Write connect_facebook Write connect_gmb Write connect_hashnode Write connect_instagram Write connect_lemmy Write connect_linkedin Write connect_linkedin-page Write connect_mastodon Write connect_nostr Write connect_pinterest Write connect_platform Write connect_producthunt Write connect_slack Write connect_telegram Write connect_threads Write connect_tiktok Write connect_whop Write connect_x Write connect_youtube Write create_ad_campaign Write create_ad_creative Write create_brand_voice Write create_goal Write create_library_item Write create_project Write create_scheduled_report Write create_upload_session Write create_workflow Write critique_post Write disconnect_connector Write draft_reply Write duplicate_scheduled_post Write edit_post Write edit_scheduled_post Write generate_ai_media Write generate_content Write generate_post_bundle Write generate_project_strategy Write import_project_source Write preview_content Write publish_ai Write publish_content Write publish_from_library Write reject_post Write reply_to_comment Write reply_to_conversation Write request_project_content Write requeue_dead_letter Write retry_scheduled_post Write save_project_content_to_library Write save_to_library Write schedule_content Write schedule_content_advanced Write schedule_multilang_content Write set_default_brand_voice Write suggest_next_schedule_time Write suggest_queue_slots Write summarize_mentions Write update_ad_campaign Write update_agent_policy Write update_calendar_event Write update_conversation Write update_library_item Write update_recurring_series Write update_workflow Write upload_media Write upvote_product

READ 57 tools

Read analyze_project Read autopilot_get_progress Read autopilot_list_goals Read check_ai_media_status Read escalate_to_support Read get_ad_performance Read get_agent_policies Read get_agent_run Read get_analytics Read get_anomaly_alerts Read get_approval_comments Read get_attribution_report Read get_audit_log Read get_benchmark_comparison Read get_best_times Read get_calendar_gaps Read get_calendar_recommendations Read get_connector_capabilities Read get_connector_health Read get_conversation Read get_inbox_summary Read get_library_item Read get_platform_requirements Read get_platform_settings_schema Read get_post_analytics Read get_producthunt_analytics Read get_project_analysis Read get_scheduled_post Read get_scheduled_posts Read get_tiktok_creator_info Read get_unified_ad_report Read get_unified_analytics Read get_upload_session Read get_workflow_run Read list_ad_accounts Read list_ad_campaigns Read list_agent_runs Read list_agents Read list_analytics_reports Read list_brand_voices Read list_calendar_events Read list_connected_accounts Read list_connected_connectors Read list_connectors Read list_conversations Read list_dead_letter Read list_inbox Read list_library Read list_media_assets Read list_pending_approvals Read list_projects Read list_recurring_series Read list_teams Read list_workflow_runs Read list_workflows Read repurpose_url Read validate_content

FAQ

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

Yes. The SendIt server exposes 5 destructive tools including cancel_recurring_series, delete_library_item, delete_post. 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 SendIt? +

The SendIt server has 79 write tools including approve_post, autopilot_approve_plan, autopilot_generate_plan. 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 SendIt.

How many tools does the SendIt MCP server expose? +

148 tools across 4 categories: Destructive, Execute, Read, Write. 57 are read-only. 91 can modify, create, or delete data.

How do I enforce a policy on SendIt? +

Register the SendIt 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 SendIt tool call.

Deterministic rules across all 148 SendIt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE SENDIT →

Free to start. No card required.

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

SendIt

// TOOL MAP

// CONTEXT-WINDOW COST

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 148 SENDIT TOOLS

// FAQ