// MCP TOOL REFERENCE

THUMBGATE TOOLS

29 tools from the ThumbGate MCP Server, categorised by risk level.

View the ThumbGate policy → Token cost: 2,575 tokens →

// ALL 29 THUMBGATE TOOLS

READ 18 tools

Read capture_feedback Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarificatio... Read capture_memory_feedback Capture success/failure feedback to harden future workflows. Aliased to capture_feedback. Read commerce_recall Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pri... Read construct_context_pack Construct a bounded context pack from contextfs Read context_provenance Get recent context/provenance events Read dashboard Get full RLHF dashboard -- approval rate, gate stats, prevention impact, system health Read describe_reliability_entity Get the definition and state of a business entity (Customer, Revenue, Funnel). Aliased to describe_semantic... Read describe_semantic_entity Get the canonical definition and state of a business entity (Customer, Revenue, Funnel). Read diagnose_failure Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints. Read evaluate_context_pack Record evaluation outcome for a context pack Read feedback_stats Get feedback stats and recommendations Read feedback_summary Get summary of recent feedback Read gate_stats Get gate enforcement statistics -- blocked count, warned count, top gates Read get_business_metrics Retrieve high-level business metrics (Revenue, Conversion, Customers) from the Semantic Layer. Read get_reliability_rules Retrieve active prevention rules and success patterns. Aliased to prevention_rules. Read list_intents List available intent plans and whether each requires human approval in the active profile Read prevention_rules Generate prevention rules from repeated mistake patterns Read satisfy_gate Satisfy a gate condition (e.g., after checking PR threads). Evidence is stored with a 5-minute TTL.

WRITE 7 tools

Write complete_handoff Complete a sequential delegation handoff and record verification outcomes Write estimate_uncertainty Estimate Bayesian uncertainty for a set of tags based on past feedback. Write export_databricks_bundle Export RLHF logs and proof artifacts as a Databricks-ready analytics bundle Write export_dpo_pairs Export DPO preference pairs from local memory log Write generate_skill Auto-generate Claude skills from repeated feedback patterns. Clusters failure patterns by tags and produces... Write plan_intent Generate an intent execution plan with policy checkpoints Write session_handoff Write a session handoff primer that auto-captures git state (branch, last 5 commits, modified files), last ...

EXECUTE 4 tools

Execute bootstrap_internal_agent Normalize a GitHub/Slack/Linear trigger into startup context, construct a recall pack, prepare a git worktr... Execute recall Recall relevant past feedback, memories, and prevention rules for the current task. Call this at the start ... Execute session_primer Read the most recent session handoff primer to restore context from the previous session. Call at session s... Execute start_handoff Start a sequential delegation handoff from a delegation-eligible intent plan

// FAQ

How many tools does the ThumbGate MCP server have? +

The ThumbGate MCP server exposes 29 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on ThumbGate tools? +

Route the ThumbGate server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do ThumbGate tools fall into? +

ThumbGate tools are categorised as Read (18), Write (7), Execute (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.