# thumbgate

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add rlhf-loop/thumbgate

# Browse available tools
npx -y @smithery/cli@latest tool list rlhf-loop/thumbgate

# Get full schema for a tool
npx -y @smithery/cli@latest tool get rlhf-loop/thumbgate capture_feedback

# Call a tool
npx -y @smithery/cli@latest tool call rlhf-loop/thumbgate capture_feedback '{}'
```

## Direct MCP Connection

Endpoint: `https://thumbgate--rlhf-loop.run.tools`

## Tools (68)

- `capture_feedback` — Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarification prompt ins…
- `feedback_summary` — Get summary of recent feedback
- `search_lessons` — Search promoted lessons and show the corrective actions, lifecycle state, prevention rules, gates, and next harness fix…
- `retrieve_lessons` — Retrieve the most relevant lessons for a given tool/action context. Use in PreToolUse hooks for per-action guidance.
- `search_thumbgate` — Search raw ThumbGate state across feedback logs, ContextFS memory, prevention rules, and imported policy documents.
- `import_document` — Import a local policy or runbook document into ThumbGate, normalize it for search, and propose provenance-backed gate c…
- `list_imported_documents` — List imported policy and runbook documents stored in local ThumbGate state.
- `get_imported_document` — Read a previously imported document with its proposed gate candidates and provenance.
- `feedback_stats` — Get feedback stats and recommendations
- `diagnose_failure` — Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints.
- `infer_lesson_from_history` — Perform autonomous inference on chat history to identify why a failure occurred and what rule should be recorded.
- `list_intents` — List available intent plans and whether each requires human approval in the active profile
- `plan_intent` — Generate an intent execution plan with policy checkpoints
- `start_handoff` — Start a sequential delegation handoff from a delegation-eligible intent plan
- `complete_handoff` — Complete a sequential delegation handoff and record verification outcomes
- `describe_reliability_entity` — Get the definition and state of a business entity (Customer, Revenue, Funnel). Aliased to describe_semantic_entity.
- `get_reliability_rules` — Retrieve active prevention rules and success patterns. Aliased to prevention_rules.
- `enforcement_matrix` — Show the full Enforcement Matrix: feedback pipeline stats, active pre-action gates, and rejection ledger with revival c…
- `security_scan` — Scan code for OWASP vulnerabilities (injection, XSS, path traversal, SSRF, prototype pollution) and supply chain risks …
- `capture_memory_feedback` — Capture success/failure feedback to harden future workflows. Aliased to capture_feedback.
- `bootstrap_internal_agent` — Normalize a GitHub/Slack/Linear trigger into startup context, construct a recall pack, prepare a git worktree sandbox, …
- `prevention_rules` — Generate prevention rules from repeated mistake patterns
- `export_dpo_pairs` — Export DPO preference pairs from local memory log
- `export_hf_dataset` — Export ThumbGate agent traces and DPO preference pairs as a HuggingFace-compatible dataset. Produces traces.jsonl, pref…
- `export_databricks_bundle` — Export ThumbGate logs and proof artifacts as a Databricks-ready analytics bundle
- `construct_context_pack` — Construct a bounded context pack from contextfs
- `evaluate_context_pack` — Record evaluation outcome for a context pack
- `context_provenance` — Get recent context/provenance events
- `generate_skill` — Auto-generate Claude skills from repeated feedback patterns. Clusters failure patterns by tags and produces SKILL.md fi…
- `recall` — Recall relevant past feedback, memories, and prevention rules for the current task. Call this at the start of any task …
- `unified_context` — Assemble a complete, role-aware context object in one call. Combines session state, user profile, relevant lessons, pre…
- `satisfy_gate` — Satisfy a gate condition with optional structured reasoning. Evidence is stored with a 5-minute TTL. When structuredRea…
- `set_task_scope` — Declare or clear the current task scope so ThumbGate can compare affected files and diffs against the approved path set.
- `get_scope_state` — Return the active task scope and any unexpired protected-file approvals.
- `set_branch_governance` — Declare or clear branch and release governance so PR, merge, release, and publish actions can be evaluated against expl…
- `get_branch_governance` — Return the active branch and release governance state.
- `approve_protected_action` — Grant a time-limited approval for edits or publish actions that touch protected files.
- `track_action` — Record a verification action in the current session (for example figma_verified or tests_passed). Session actions expir…
- `verify_claim` — Check whether a claim has enough tracked evidence before the agent asserts it.
- `check_operational_integrity` — Evaluate whether the current repo state is safe for PR, merge, release, and publish operations.
- `workflow_sentinel` — Predict pre-action workflow risk, blast radius, and remediations before a tool call executes.
- `register_claim_gate` — Register a custom claim verification rule in local runtime state without editing tracked repo config.
- `gate_stats` — Get gate enforcement statistics -- blocked count, warned count, top gates
- `dashboard` — Get full ThumbGate dashboard -- Harness Score, gate stats, prevention impact, proof, and system health
- `org_dashboard` — Org-wide multi-agent dashboard — shows all active agents, gate decisions, adherence rates, risk agents, and top blocked…
- `settings_status` — Resolve managed, user, project, and local ThumbGate settings with per-field origin metadata for policy visibility.
- `commerce_recall` — Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pricing, regula…
- `get_business_metrics` — Retrieve high-level business metrics (Revenue, Conversion, Customers) from the Semantic Layer.
- `describe_semantic_entity` — Get the canonical definition and state of a business entity (Customer, Revenue, Funnel).
- `estimate_uncertainty` — Estimate Bayesian uncertainty for a set of tags based on past feedback.
- `session_handoff` — Write a session handoff primer that auto-captures git state (branch, last 5 commits, modified files), last completed ta…
- `session_primer` — Read the most recent session handoff primer to restore context from the previous session. Call at session start.
- `list_harnesses` — List natural-language harness specs for portable workflow control, proof-backed verification, and GTM execution.
- `run_harness` — Execute a natural-language harness through the async job runner with checkpoints, verification, and proof-backed outcom…
- `schedule` — Create, list, or delete scheduled tasks. Supports natural language scheduling like "daily 9:00", "weekly monday 8:30", …
- `user_profile` — Manage persistent user profile — preferences, style, domain knowledge that persists across sessions. Actions: add, remo…
- `session_search` — Search past session notes and conversations using full-text search. Returns relevant sessions from the SQLite FTS5 inde…
- `open_feedback_session` — Open a feedback session after thumbs up/down. Follow-up messages will be captured for 60s.
- `append_feedback_context` — Append a follow-up message to an open feedback session. Call this when the user types additional context after giving t…
- `finalize_feedback_session` — Finalize a feedback session and re-infer the lesson with all follow-up context.
- `webhook_deliver` — Send a message to Teams, Slack, or Discord via webhook. Use for status reports, alerts, and notifications.
- `reflect_on_feedback` — Run a post-mortem analysis on negative feedback. Returns a proposed rule and recurrence info.

---
*Response truncated. Use `npx -y @smithery/cli@latest` for complete data.*