29 tools from the ThumbGate MCP Server, categorised by risk level.
View the ThumbGate policy →capture_feedback Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarification prompt instead of memory promotion. capture_memory_feedback Capture success/failure feedback to harden future workflows. Aliased to capture_feedback. commerce_recall Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pricing, regulatory). Returns quality score... 2/5 construct_context_pack Construct a bounded context pack from contextfs 2/5 context_provenance Get recent context/provenance events dashboard Get full RLHF dashboard -- approval rate, gate stats, prevention impact, system health describe_reliability_entity Get the definition and state of a business entity (Customer, Revenue, Funnel). Aliased to describe_semantic_entity. describe_semantic_entity Get the canonical definition and state of a business entity (Customer, Revenue, Funnel). diagnose_failure Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints. evaluate_context_pack Record evaluation outcome for a context pack feedback_stats Get feedback stats and recommendations feedback_summary Get summary of recent feedback gate_stats Get gate enforcement statistics -- blocked count, warned count, top gates get_business_metrics Retrieve high-level business metrics (Revenue, Conversion, Customers) from the Semantic Layer. get_reliability_rules Retrieve active prevention rules and success patterns. Aliased to prevention_rules. list_intents List available intent plans and whether each requires human approval in the active profile prevention_rules Generate prevention rules from repeated mistake patterns satisfy_gate Satisfy a gate condition (e.g., after checking PR threads). Evidence is stored with a 5-minute TTL. complete_handoff Complete a sequential delegation handoff and record verification outcomes 2/5 estimate_uncertainty Estimate Bayesian uncertainty for a set of tags based on past feedback. 2/5 export_databricks_bundle Export RLHF logs and proof artifacts as a Databricks-ready analytics bundle 2/5 export_dpo_pairs Export DPO preference pairs from local memory log 2/5 generate_skill Auto-generate Claude skills from repeated feedback patterns. Clusters failure patterns by tags and produces SKILL.md files with DO/INSTEAD rules. 2/5 plan_intent Generate an intent execution plan with policy checkpoints 2/5 session_handoff Write a session handoff primer that auto-captures git state (branch, last 5 commits, modified files), last completed task, next step, and blockers.... 2/5 bootstrap_internal_agent Normalize a GitHub/Slack/Linear trigger into startup context, construct a recall pack, prepare a git worktree sandbox, and emit an execution plus r... 4/5 recall Recall relevant past feedback, memories, and prevention rules for the current task. Call this at the start of any task to inject past learnings int... 4/5 session_primer Read the most recent session handoff primer to restore context from the previous session. Call at session start. 3/5 start_handoff Start a sequential delegation handoff from a delegation-eligible intent plan 3/5 The ThumbGate MCP server exposes 29 tools across 3 categories: Read, Write, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the ThumbGate server.
ThumbGate tools are categorised as Read (18), Write (7), Execute (4). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept