ThumbGate
MCP Memory Gateway captures explicit structured feedback from AI coding agents, validates it against a rubric engine, and auto-promotes repeated failures into…
What it can do
- 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.
- Feedback Summary: Get summary of recent feedback
- Feedback Stats: Get feedback stats and recommendations
What data it sees
Do you need an account
No: the server works without sign-in
MCP Memory Gateway captures explicit structured feedback from AI coding agents, validates it against a rubric engine, and auto-promotes repeated failures into prevention rules enforced via PreToolUse hooks. Pre-action gates physically block tool calls matching known failure patterns before execution — turning past mistakes into hard constraints rather than suggestions. Supports semantic recall via LanceDB vectors, DPO/KTO export for downstream fine-tuning, and a file watcher bridge for external signal ingestion. Compatible with Claude Code, Codex, Gemini, Amp, Cursor, and OpenCode. Install with npx mcp-memory-gateway init or claude mcp add rlhf -- npx -y mcp-memory-gateway serve. MIT licensed, open source.
How to connect
How to connect ThumbGate to Claude
The server address to paste into Claude settings:
https://mcp-memory-gateway-v2--rlhf-loop.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect ThumbGate to ChatGPT
The server address to paste into ChatGPT settings:
https://mcp-memory-gateway-v2--rlhf-loop.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect ThumbGate to Cursor
The server address to paste into Cursor settings:
https://mcp-memory-gateway-v2--rlhf-loop.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (29)
Raw names from tools/list. Only developers need these.
| 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. |
| feedback_summary | Get summary of recent feedback |
| feedback_stats | Get feedback stats and recommendations |
| diagnose_failure | Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints. |
| 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. |
| 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, and emit an execution plus reviewer-lane plan. |
| prevention_rules | Generate prevention rules from repeated mistake patterns |
| export_dpo_pairs | Export DPO preference pairs from local memory log |
| export_databricks_bundle | Export RLHF 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 files with DO/INSTEAD rules. |
| 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 into the conversation. |
| satisfy_gate | Satisfy a gate condition (e.g., after checking PR threads). Evidence is stored with a 5-minute TTL. |
| gate_stats | Get gate enforcement statistics -- blocked count, warned count, top gates |
| dashboard | Get full RLHF dashboard -- approval rate, gate stats, prevention impact, system health |
| commerce_recall | Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pricing, regulatory). Returns quality scores alongside memories for agentic commerce agents. |
| 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 task, next step, and blockers. The next session reads this automatically for seamless context continuity. |
| session_primer | Read the most recent session handoff primer to restore context from the previous session. Call at session start. |