MemHeaven — Self-hosted Remote MCP Memory for ChatGPT
Gives ChatGPT and other remote AI clients long-term memory you can search, inspect, and delete. Deploys to Cloudflare's free tier using Workers, D1, R2, Vectorize, and Workers AI for embeddings, so no VM or database admin needed. Exposes MemPalace-style tools for storing context in drawers, diaries, and knowledge graphs, with semantic search over chunked content. OAuth 2.1 with PKCE handles authorization, and everything is tenant-scoped with quota guardrails. Reach for this when you want continuity across ChatGPT sessions or coding agents that need to remember project decisions, but you want the memory layer remote and self-hosted instead of locked into a provider's black box.
- GitHub stars
- 2
- tools
- 34
- transport
- HTTP
- last updated
- Aug 13, 2026
Tools
34 toolsPublic tool metadata for what this MCP can expose to an agent.
mempalace_statusDiagnostics and backend capabilities for memory-relevant chats.
Diagnostics and backend capabilities for memory-relevant chats.
No parameter schema in public metadata yet.
mempalace_wake_contextStart a memory-relevant chat with bounded, privacy-scoped startup context.
Start a memory-relevant chat with bounded, privacy-scoped startup context.
No parameter schema in public metadata yet.
mempalace_list_wingsList tenant-scoped wings and active drawer counts.
List tenant-scoped wings and active drawer counts.
No parameter schema in public metadata yet.
mempalace_list_roomsList tenant-scoped rooms and active drawer counts for one wing or all wings.
List tenant-scoped rooms and active drawer counts for one wing or all wings.
No parameter schema in public metadata yet.
mempalace_get_taxonomyReturn the current tenant-scoped wing and room taxonomy.
Return the current tenant-scoped wing and room taxonomy.
No parameter schema in public metadata yet.
mempalace_get_aaak_specReturn compact guidance for concise, readable memory notes.
Return compact guidance for concise, readable memory notes.
No parameter schema in public metadata yet.
mempalace_searchSearch tenant-scoped drawers with hybrid semantic and lexical retrieval.
Search tenant-scoped drawers with hybrid semantic and lexical retrieval.
No parameter schema in public metadata yet.
mempalace_check_duplicateCheck for exact or semantic duplicates before writing memory.
Check for exact or semantic duplicates before writing memory.
No parameter schema in public metadata yet.
mempalace_get_drawerFetch one tenant-scoped drawer with bounded content and provenance.
Fetch one tenant-scoped drawer with bounded content and provenance.
No parameter schema in public metadata yet.
mempalace_list_drawersList active tenant-scoped drawers with optional wing and room filters.
List active tenant-scoped drawers with optional wing and room filters.
No parameter schema in public metadata yet.
mempalace_add_drawerAdd durable drawer content and index it semantically.
Add durable drawer content and index it semantically.
No parameter schema in public metadata yet.
mempalace_update_drawerUpdate a drawer and reindex changed content or metadata.
Update a drawer and reindex changed content or metadata.
No parameter schema in public metadata yet.
mempalace_delete_drawerSoft-delete a tenant-scoped drawer and remove its semantic index entries.
Soft-delete a tenant-scoped drawer and remove its semantic index entries.
No parameter schema in public metadata yet.
mempalace_diary_writeWrite a concise diary entry and index it for scoped search.
Write a concise diary entry and index it for scoped search.
No parameter schema in public metadata yet.
mempalace_diary_readRead recent diary entries with optional wing and room filters.
Read recent diary entries with optional wing and room filters.
No parameter schema in public metadata yet.
mempalace_diary_searchSearch diary entries for one explicit agent with hard scope filters.
Search diary entries for one explicit agent with hard scope filters.
No parameter schema in public metadata yet.
mempalace_diary_reindexBackfill or refresh diary semantic index rows for the tenant.
Backfill or refresh diary semantic index rows for the tenant.
No parameter schema in public metadata yet.
mempalace_kg_queryQuery tenant-scoped temporal knowledge-graph facts.
Query tenant-scoped temporal knowledge-graph facts.
No parameter schema in public metadata yet.
mempalace_kg_checkRun deterministic reliability checks for active KG conflicts and stale facts.
Run deterministic reliability checks for active KG conflicts and stale facts.
No parameter schema in public metadata yet.
mempalace_kg_addAdd a tenant-scoped temporal knowledge-graph fact.
Add a tenant-scoped temporal knowledge-graph fact.
No parameter schema in public metadata yet.
mempalace_kg_invalidateInvalidate an exact tenant-scoped knowledge-graph fact.
Invalidate an exact tenant-scoped knowledge-graph fact.
No parameter schema in public metadata yet.
mempalace_kg_timelineShow the recent knowledge-graph timeline for an entity or all facts.
Show the recent knowledge-graph timeline for an entity or all facts.
No parameter schema in public metadata yet.
mempalace_kg_statsReturn tenant-scoped knowledge-graph statistics.
Return tenant-scoped knowledge-graph statistics.
No parameter schema in public metadata yet.
mempalace_traverseTraverse the tenant shared-room graph and explicit tunnels.
Traverse the tenant shared-room graph and explicit tunnels.
No parameter schema in public metadata yet.
mempalace_find_tunnelsFind tenant-scoped cross-wing shared rooms that behave like passive tunnels.
Find tenant-scoped cross-wing shared rooms that behave like passive tunnels.
No parameter schema in public metadata yet.
mempalace_graph_statsReturn tenant-scoped graph, shared-room, and explicit tunnel statistics.
Return tenant-scoped graph, shared-room, and explicit tunnel statistics.
No parameter schema in public metadata yet.
mempalace_create_tunnelCreate an explicit tenant-scoped tunnel between wing and room locations.
Create an explicit tenant-scoped tunnel between wing and room locations.
No parameter schema in public metadata yet.
mempalace_list_tunnelsList tenant-scoped explicit tunnels, optionally filtered by endpoint wing.
List tenant-scoped explicit tunnels, optionally filtered by endpoint wing.
No parameter schema in public metadata yet.
mempalace_delete_tunnelDelete a tenant-scoped explicit tunnel by ID.
Delete a tenant-scoped explicit tunnel by ID.
No parameter schema in public metadata yet.
mempalace_follow_tunnelsFollow explicit tunnels connected to a wing and room location.
Follow explicit tunnels connected to a wing and room location.
No parameter schema in public metadata yet.
mempalace_hook_settingsReturn the configured save policy for this deployment.
Return the configured save policy for this deployment.
No parameter schema in public metadata yet.
mempalace_memories_filed_awayReturn the latest tenant-scoped write filing status.
Return the latest tenant-scoped write filing status.
No parameter schema in public metadata yet.
mempalace_reconnectReturn configured binding and index health.
Return configured binding and index health.
No parameter schema in public metadata yet.
mempalace_syncReport that local filesystem and git sync is unsupported in hosted mode.
Report that local filesystem and git sync is unsupported in hosted mode.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
MemHeaven logo
MemHeaven
MemHeaven is a self-hosted remote MCP memory server for ChatGPT and other cloud AI agents.
It gives hosted AI clients searchable long-term memory you own, deployed on Cloudflare. MemHeaven is inspired by MemPalace's long-term-memory model while using a remote deployment shape for hosted clients.
Deploy on a Cloudflare Free account. No VM, no Docker, no database admin.
Free-tier limits apply; heavy usage may require paid Cloudflare usage.
Quick links: Quickstart · Getting started from zero · ChatGPT setup · Client compatibility · Security model · Behavior evals
What problem it solves
AI assistants are useful in the moment, but they often forget project context across chats, sessions, and tools.
Details
- Repository
- github.com/nazar256/memheaven
- Website
- nazar256.github.io/memheaven
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
No Crdnogoo9/no-crdDynamic pod spawner & proxy for ephemeral AI agent workspaces on Kubernetes without CRDs2stars
Pqs Mcp Serveronchainaiintel/pqs-mcp-serverPQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.2stars
Spec Score Mcpopenpoem/spec-score-mcpScore your specs before feeding them to an LLM. MCP server with radar chart visualization.2stars
Bolor Brain Mcpphotoxpedia/bolor-brain-mcpCognitive architecture MCP server with memory, learning, and contextual understanding2stars
Hindsight MCPrbfinch/hindsight-mcpMCP server for AI-assisted coding with development history: git, tests, Copilot.2stars
Resemble AIresemble-ai/resemble-mcpResemble AI: deepfake, AI-text, and site agent detection, Detect Agents, intelligence, watermarks.2stars