29 tools. 29 can modify or destroy data without limits.
1 destructive tool with no built-in limits. Policy required.
Last updated:
Destructive tools (np_squeeze) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (np_arange, np_array, np_concatenate) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and Mcp Numpy. 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 @mcp-numpy np_squeeze:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
np_arange:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
Yes. The Mcp Numpy server exposes 1 destructive tools including np_squeeze. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Mcp Numpy server has 28 write tools including np_arange, np_array, np_concatenate. 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.
29 tools across 2 categories: Destructive, Write. 0 are read-only. 29 can modify, create, or delete data.
One line change. Instead of running the Mcp Numpy server directly, prefix it with Intercept: intercept -c io-github-daedalus-mcp-numpy.yaml -- npx -y @mcp-numpy. Download a pre-built policy from policylayer.com/policies/io-github-daedalus-mcp-numpy and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init