@IgorGanapolsky
Basic information
MCP Memory Gateway is a pre-action gate engine for AI coding agents. Unlike memory servers that store and retrieve context (Mem0, Zep), this server enforces behavior change: repeated failures are auto-promoted into prevention rules, and PreToolUse hooks physically block tool call
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-memory-gateway": {
"command": "npx",
"args": [
"-y",
"mcp-memory-gateway",
"serve"
]
}
}
}Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarification prompt instead of memory promotion.
Get summary of recent feedback
Search promoted lessons and show the corrective actions, lifecycle state, prevention rules, gates, and next harness fixes linked to each result.
Retrieve the most relevant lessons for a given tool/action context. Use in PreToolUse hooks for per-action guidance.
Search raw ThumbGate state across feedback logs, ContextFS memory, and prevention rules.
Get feedback stats and recommendations
Diagnose a failed or suspect workflow step using MCP schema, workflow, gate, and approval constraints.
Perform autonomous inference on chat history to identify why a failure occurred and what rule should be recorded.
List available intent plans and whether each requires human approval in the active profile
Generate an intent execution plan with policy checkpoints
Start a sequential delegation handoff from a delegation-eligible intent plan
Complete a sequential delegation handoff and record verification outcomes
Get the definition and state of a business entity (Customer, Revenue, Funnel). Aliased to describe_semantic_entity.
Retrieve active prevention rules and success patterns. Aliased to prevention_rules.
Show the full Enforcement Matrix: feedback pipeline stats, active pre-action gates, and rejection ledger with revival conditions.
Capture success/failure feedback to harden future workflows. Aliased to capture_feedback.
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.
Generate prevention rules from repeated mistake patterns
Export DPO preference pairs from local memory log
Export ThumbGate logs and proof artifacts as a Databricks-ready analytics bundle
Construct a bounded context pack from contextfs
Record evaluation outcome for a context pack
Get recent context/provenance events
Auto-generate Claude skills from repeated feedback patterns. Clusters failure patterns by tags and produces SKILL.md files with DO/INSTEAD rules.
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 a gate condition with optional structured reasoning. Evidence is stored with a 5-minute TTL. When structuredReasoning is provided, the premise/evidence/conclusion chain is stored in the audit trail.
Record a verification action in the current session (for example figma_verified or tests_passed). Session actions expire after one hour.
Check whether a claim has enough tracked evidence before the agent asserts it.
Register a custom claim verification rule in local runtime state without editing tracked repo config.
Get gate enforcement statistics -- blocked count, warned count, top gates
Get full ThumbGate dashboard -- Harness Score, gate stats, prevention impact, proof, and system health
Org-wide multi-agent dashboard — shows all active agents, gate decisions, adherence rates, risk agents, and top blocked gates across the organization. Team rollout: full visibility. Free preview: limited to 3 agents.
Resolve managed, user, project, and local ThumbGate settings with per-field origin metadata for policy visibility.
Recall past feedback filtered by commerce categories (product_recommendation, brand_compliance, sizing, pricing, regulatory). Returns quality scores alongside memories for agentic commerce agents.
Retrieve high-level business metrics (Revenue, Conversion, Customers) from the Semantic Layer.
Get the canonical definition and state of a business entity (Customer, Revenue, Funnel).
Estimate Bayesian uncertainty for a set of tags based on past feedback.
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.
Read the most recent session handoff primer to restore context from the previous session. Call at session start.
List natural-language harness specs for portable workflow control, proof-backed verification, and GTM execution.
Execute a natural-language harness through the async job runner with checkpoints, verification, and proof-backed outcomes.
Create, list, or delete scheduled tasks. Supports natural language scheduling like "daily 9:00", "weekly monday 8:30", "hourly". Installs as macOS LaunchAgent or Linux crontab.
Manage persistent user profile — preferences, style, domain knowledge that persists across sessions. Actions: add, remove, replace, view.
Search past session notes and conversations using full-text search. Returns relevant sessions from the SQLite FTS5 index for cross-session recall.
Open a feedback session after thumbs up/down. Follow-up messages will be captured for 60s.
Append a follow-up message to an open feedback session. Call this when the user types additional context after giving thumbs up/down.
Finalize a feedback session and re-infer the lesson with all follow-up context.
Send a message to Teams, Slack, or Discord via webhook. Use for status reports, alerts, and notifications.
Run a post-mortem analysis on negative feedback. Returns a proposed rule and recurrence info.
Report a bug, suggestion, or complaint about ThumbGate itself (not project feedback). Auto-files a GitHub issue with system context. Use when the user expresses frustration or requests a feature for the mcp-memory-gateway tool.
Mcp Memory Gateway is a pre-action gate engine for AI coding agents. Unlike memory servers that store and retrieve context, it enforces behavior change by auto-promoting repeated failures into prevention rules and physically blocking tool calls that match known failure patterns before they execute. It captures structured up/down feedback, validates against a rubric engine, promotes to searchable JSONL and LanceDB vector memory, and recalls relevant context at session start.
Install with npx mcp-memory-gateway init. It works with Claude Code, Codex, Gemini, Amp, Cursor, and any MCP-compatible agent. No further configuration or invocation details are provided in the README.
Mcp Memory Gateway is a pre-action gate engine that enforces behavior change by blocking tool calls that match known failure patterns, rather than simply storing and retrieving context.
The README does not specify runtime or dependencies beyond being installable via `npx mcp-memory-gateway init`.
Memory is stored in searchable JSONL files and LanceDB vector memory.
It works with Claude Code, Codex, Gemini, Amp, Cursor, and any MCP-compatible agent.
Yes, it captures structured up/down feedback and validates it against a rubric engine, rejecting vague signals.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths
MCP connector for Snipara, the Project Brain for AI coding agents
Comments