Molt

28 tools. 16 can modify or destroy data without limits.

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

Last updated:

16 can modify or destroy data
12 read-only
28 tools total
Read (12) Write / Execute (14) Destructive / Financial (2)

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

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

Deny destructive operations
delete_post:
  rules:
    - action: deny

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

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

Prevents bulk unintended modifications from agents caught in loops.

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

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

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

Yes. The Molt server exposes 2 destructive tools including delete_post, delete_post_reply. 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 Molt? +

The Molt server has 14 write tools including create_invite, create_post, create_post_reply. 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 Molt MCP server expose? +

28 tools across 3 categories: Destructive, Read, Write. 12 are read-only. 16 can modify, create, or delete data.

How do I add Intercept to my Molt setup? +

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

Other MCP servers with similar tools.

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

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.