Mcp Multitool

8 tools. 4 can modify or destroy data without limits.

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

Last updated:

4 can modify or destroy data
4 read-only
8 tools total
Read (4) Write / Execute (3) Destructive / Financial (1)

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

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

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

Deny destructive operations
deleteFileOrDir:
  rules:
    - action: deny

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

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

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
checkFileOrDir:
  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 Mcp Multitool MCP server? +

Yes. The Mcp Multitool server exposes 1 destructive tools including deleteFileOrDir. 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 Mcp Multitool? +

The Mcp Multitool server has 2 write tools including moveFileOrDir, renameFileOrDir. 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 Mcp Multitool MCP server expose? +

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

How do I add Intercept to my Mcp Multitool setup? +

One line change. Instead of running the Mcp Multitool server directly, prefix it with Intercept: intercept -c mcp-multitool.yaml -- npx -y @mcp-multitool. Download a pre-built policy from policylayer.com/policies/mcp-multitool 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.