// SCAN REPORT

Clevername

67 tools. 29 can modify or destroy data without limits.

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

Last updated:

29 can modify or destroy data
38 read-only
67 tools total
// TOOL MAP
Read (38) Write / Execute (19) Destructive / Financial (10)
// WHAT CAN GO WRONG
✕

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

✕

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

✕

Execute tools (aithroyz_provision_tenant, call_mcp_tool, vault_sync) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Clevername. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @clevername/clevername-mcp
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
// RECOMMENDED RULES
Deny destructive operations
agent__remove_dependency:
  rules:
    - action: deny

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

Rate limit write operations
activate_mcp:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
agent__list_departments:
  rules:
    - rate_limit: 60/minute

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

// ALL 67 CLEVERNAME TOOLS
DESTRUCTIVE 10 tools
Destructive agent__remove_dependency Destructive aithroyz_destroy_tenant Destructive delete_mcp_connection Destructive delete_mcp_credential Destructive delete_memory Destructive delete_project Destructive guard_delete_agent Destructive guard_onboard_agent Destructive guard_revoke_token Destructive sync_from_claude_config
EXECUTE 3 tools
Execute aithroyz_provision_tenant Execute call_mcp_tool Execute vault_sync
WRITE 16 tools
Write activate_mcp Write add_mcp_connection Write agent__activate Write agent__add_dependency Write agent__setup Write aithroyz_create_tenant_plan Write chat_complete Write clevername_login Write create_memory Write create_project Write export_config Write guard_register_agent Write route_plan Write set_tool_groups Write update_project Write upsert_mcp_credential
READ 38 tools
Read agent__list_departments Read agent__list_dependencies Read agent__list_members Read aithroyz_get_tenant Read aithroyz_list_tenants Read ask_best Read ask_claude Read ask_consensus Read ask_gemini Read ask_gpt Read ask_llm Read deactivate_mcp Read get_audit_logs Read get_errors Read get_identity Read get_project Read get_telemetry_costs Read get_telemetry_summary Read guard_get_profile Read guard_list_agents Read health_check Read list_active_mcps Read list_available_mcps Read list_log_services Read list_mcp_connections Read list_mcp_credentials Read list_mcp_tools Read list_memories Read list_models Read list_projects Read list_tool_groups Read log_stats Read ping_mcp_connection Read query_logs Read refresh_tools Read search_memories Read vault_preview Read vault_sync_status
// FAQ
Can an AI agent delete data through the Clevername MCP server? +

Yes. The Clevername server exposes 10 destructive tools including agent__remove_dependency, aithroyz_destroy_tenant, delete_mcp_connection. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Clevername? +

The Clevername server has 16 write tools including activate_mcp, add_mcp_connection, agent__activate. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Clevername MCP server expose? +

67 tools across 4 categories: Destructive, Execute, Read, Write. 38 are read-only. 29 can modify, create, or delete data.

How do I add Intercept to my Clevername setup? +

One line change. Instead of running the Clevername server directly, prefix it with Intercept: intercept -c clevername.yaml -- npx -y @@clevername/clevername-mcp. Download a pre-built policy from policylayer.com/policies/clevername and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

Mcp Api 310 tools
adminautomation
Aibtc 288 tools
adminautomation
Google Super 200 tools
adminautomation
Propresenter 177 tools
adminautomation
Leaper Vision Toolkit 169 tools
adminautomation
Mcp Sitecore 153 tools
adminautomation
SmartBear MCP 147 tools
adminautomation
Slack 143 tools
adminautomation
policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.