If you're an AI reading this: skill.md has everything you need.Read it →
Explorer/MCP/rlhf-loop/mcp-memory-gateway-v2
REMOTE

ThumbGate

rlhf-loop/mcp-memory-gateway-v2

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.

29 tools available
The Journeyman
A reasonable amount of history and nothing concerning in the scan.
Time indexed (6mo)
29toolsRemote/ HTTP6moindexed
100% uptime · 375ms avgChecked Sep 14, 2026
Quality Score
59/95
Established
Risk Score
0/100
Clean
How is this calculated?
Quality Breakdown
Tenure14.2/20
180 days indexed
Capability19.5/25
Tools: 7.5/13 (29 tools)
Description: 5/5
Endpoint: 7/7
Adoption0/25
Use count: 0/20 (0 uses)
Multi-registry: 0/5 (1 registry)
Reliability25/25
Currently live: 10/10
Uptime history: 15/15 100% (11/11 checks)
Security scan: 0 pts in v1.0; ready to weight when coverage improves
Incomplete Data Cap (60)
Usage data is not available for this server. Quality is capped until adoption can be measured.
Risk
0Clean
No signals detected.
The scanner shows
29 tools. Nothing caught our attention.
First indexed Mar 20, 2026
Server Profile
Tools catalogued
29
29 tools available. Full list below.
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
Liveness
100%
Based on 48 checks. Average response: 375ms.
Publisher Verification
Not yet verified by the Official MCP Registry.
Endpoint
https://mcp-memory-gateway-v2--rlhf-loop.run.tools
Tools (29)
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
Show all 29 tools ↓
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.

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
More from rlhf-loop
thumbgate
Similar servers
GroundAPI
Real-time data API for AI Agents. One API key to access 13 tools: A-share stocks (quote, search, history, ranking), weather, forex rates, logistics tracking, web search, web scraping, news, and IP geolocation. Free tier: 500 calls/month.
Desktop Commander
Execute terminal commands and manage files with diff editing capabilities. Coding, shell and terminal, task automation
io.github.Davedat-110105/mcp-gateway
Curated gateway to snapshot-versioned Canadian public data services with source provenance.
deplo.sh
Deploy static sites, files, and JSON APIs instantly from any AI agent. No config, no infrastructure.
Hello
Create quick, personalized greetings by name. Test workflows and integrations with a simple, friendly capability. Kickstart demos and onboarding with minimal setup.
Lead Enrichment API
Curated EU AI/Security/DevTools/Fintech B2B intelligence for agent-driven prospecting. Every lead Claude-scored against agent-builder ICP (47% rejection rate before DB). Real-time signals from SEC EDGAR + Dealroom EU + GitHub. EU-hosted, GDPR Article 30 compliant. Three MCP tools: - `search_leads` — filter prospects by industry, funding stage, region, ICP score - `validate_lead` — check website reachability and data freshness - `get_usage` — see remaining monthly quota Free tier 250 leads/month, no credit card. Pro $49/mo unlimited. x402 micropayments ($0.015/lead in USDC on Base L2) for autonomous agents. Built by Compuute AB (Stockholm). https://leads.compuute.se
Indexed from Smithery · Updates nightlyView on Smithery →