29 tools. 11 can modify or destroy data without limits.
11 write tools that can modify data. Rate limits recommended.
Last updated:
Write operations (complete_handoff, estimate_uncertainty, export_databricks_bundle) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (bootstrap_internal_agent, recall, session_primer) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and ThumbGate. 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 @rlhf-loop/mcp-memory-gateway-v2 complete_handoff:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
capture_feedback:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The ThumbGate server has 7 write tools including complete_handoff, estimate_uncertainty, export_databricks_bundle. 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 3 categories: Execute, Read, Write. 18 are read-only. 11 can modify, create, or delete data.
One line change. Instead of running the ThumbGate server directly, prefix it with Intercept: intercept -c rlhf-loop-mcp-memory-gateway-v2.yaml -- npx -y @rlhf-loop/mcp-memory-gateway-v2. Download a pre-built policy from policylayer.com/policies/rlhf-loop-mcp-memory-gateway-v2 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