Katashiro

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

4 write tools that can modify data. Rate limits recommended.

Last updated:

4 can modify or destroy data
5 read-only
9 tools total
Read (5) Write / Execute (4) Destructive / Financial (0)

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

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

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

Prevents bulk unintended modifications from agents caught in loops.

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

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

How do I prevent bulk modifications through Katashiro? +

The Katashiro server has 3 write tools including generate_report, generate_summary, knowledge_add_node. 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 Katashiro MCP server expose? +

9 tools across 3 categories: Execute, Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I add Intercept to my Katashiro setup? +

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