MCP App Store
by KeenEthics
Genesys icon

Genesys MCP Server for ChatGPT

By astrixlabs.ai

Overview

Genesys gives your AI a causal memory graph — not a list of remembered facts, but a living network where every memory is a node, every relationship is a typed causal edge, and every retrieval can be explained. Ask why a memory surfaced and Genesys shows its relevance score, causal connectivity, and reactivation history. Trace how memories connect and follow full causal chains from decision to consequence. Your memory graph is yours: it lives outside any single AI vendor, works identically with ChatGPT, Claude, and any MCP-compatible model, and travels with you when you switch. You control it directly — pin what matters permanently, inspect graph health at any time, and delete anything, anytime, with hard erasure. Built on neuroscience-inspired scoring (relevance × causal connectivity × reactivation), Genesys forgets safely: only memories that are irrelevant, causally orphaned, and unpinned are ever pruned.

How to connect

  1. ChatGPT: Open the Genesys listing in the ChatGPT app directory and choose Connect. ChatGPT listing Genesys exposes 24 tools here.

Tools

delete_memory

ChatGPT
Permanently delete a memory node and all its edges. Call when the user says 'forget this', 'delete that memory', 'remove that', or wants specific information erased. Always confirm with the user before deleting.

list_core_memories

ChatGPT
List all pinned/core memories, optionally filtered by category, sorted by causal weight. Call when the user asks 'what do you know about me?', 'show me my memories', 'what have you saved?', or wants an overview of stored information.

memory_amend

ChatGPT
Record a correction or update to an existing memory. Creates a NEW memory containing the corrected content and links it to the old one with a SUPERSEDES edge — the old memory is kept for provenance but automatically ranked down and tagged superseded_by in future recalls. Use when a fact changes ('my rate is now $150', 'we moved the deadline'), instead of storing a disconnected duplicate. Only the memory's owner can amend it.

memory_explain

ChatGPT
Explain a memory's score breakdown, causal basis, and removal impact.

memory_recall

ChatGPT
Recall memories using hybrid search (vector + keyword + graph spreading activation). Call this when the user references stored context or past conversations ('do you remember', 'what did I say about'), or asks a question their stored history, preferences, or past decisions would clearly improve. Also call before memory_store to find related memories to link. Results are ranked by decay_score + spreading_boost; each hit carries activation (same value as decay_score — a retention/recency weight, not a deletion countdown). Set verbosity="concise" to omit causal-chain enrichment for a much smaller payload. This tool is read-only: it does not modify memories or access history.

memory_retire_by_ref

ChatGPT
Retire the memories that cite a source that was removed. mode=amend (default): a memory whose only ref is this one is amended to a '[Retired] ...' note tagged retired (history is kept); a memory with other refs is amended with this ref removed. mode=delete: sole-ref memories are deleted and the ref is removed from the others. Needs writer or owner when space is named; without space it acts on your personal memory (services must name a space). Returns {retired, updated, deleted}.

memory_stats

ChatGPT
Get graph statistics: node counts by status, edge counts by type, orphan count.

memory_store

ChatGPT
Store a new memory in the user's persistent causal memory graph — a user-owned, inspectable, portable store of nodes linked by causal edges. Call this when the user shows intent to remember: they share something they want kept for later, ask you to remember, update, or forget information, or confirm a durable fact or decision. Do not store personal facts on your own initiative or retain details the user has not indicated they want kept. Trigger phrases: 'remember this', 'don't forget', 'update your memory', 'please forget', 'I no longer...', 'actually it's...', or any explicit request to retain or correct a fact. IMPORTANT: Before storing, call memory_recall first to find existing related memories, then link them. Prefer related = [{"id": "<uuid>", "type": "<edge type>"}] to express the TRUE relationship — valid types: caused_by, supports, contradicts, supersedes, derived_from, related_to, temporal_sequence. Use related_to (list of ids) only for plain causal links (stored as caused_by). Without links the memory becomes an orphan with no causal connections. Optional category tags the memory (e.g. "preference", "decision", "project"). The response may include possible_conflicts — surface those to the user rather than silently keeping both versions.

memory_store_batch

ChatGPT
Store up to GENESYS_BATCH_MAX_ITEMS (default 100) memories in one call, all into one space (or your personal memory when space is omitted; services must name a space). Every item is validated first; if any item is invalid nothing is stored and the error batch_invalid lists each problem with its index. Items are then stored in order; an item's related entry may be {"ref_index": i, "type": t} to link to earlier item i. Returns one result per item: {index, node_id, status: stored|exists|unchanged|amended, superseded?}. Retry safety: when every item carries an external_id the batch is idempotent, so it is safe to resend the whole batch after a timeout (unchanged items come back with the same node ids). Without external_id a resend creates duplicates.

memory_traverse

ChatGPT
Traverse the memory graph from a starting node. Returns connected nodes within depth, plus the connecting edges (source, target, type, weight, provenance) of the induced subgraph where the storage backend supports it. Filter with edge_types (e.g. ["caused_by"]) to follow only causal paths.

pin_memory

ChatGPT
Pin a memory to core status, preventing it from being forgotten.

send_feedback

ChatGPT
Send feedback about Papez straight to its maker. Use this when a Papez tool errored, returned something confusing, or when the user asks to report a bug, request a feature, or say what is working. kind is one of bug, confusion, idea, praise, other. context is optional: what you were trying to do, which tool, which client. Nothing about the user's memories is sent.

set_core_preferences

ChatGPT
Configure which categories are auto-promoted, require approval, or are excluded from core memory.

space_archive

ChatGPT
Archive a space (owner): read-only, hidden from default recall, readable when named explicitly.

space_create

ChatGPT
Create a Mind Space: a shared memory graph for a team or engagement. You become its first owner. Users only.

space_erase

ChatGPT
PERMANENTLY delete a space and every memory and edge in it (owner). confirm_slug must equal the space's slug; dry_run returns the counts without deleting.

space_get

ChatGPT
Get one space with its member and memory counts.

space_list

ChatGPT
List the spaces you are a member of, with your role and counts.

space_member_list

ChatGPT
List a space's members.

space_member_remove

ChatGPT
Remove a member from a space (owner). Takes effect on their next request.

space_unarchive

ChatGPT
Unarchive a space (owner).

space_update

ChatGPT
Change a space's name, description or policies (owner). The slug can't be changed.

unpin_memory

ChatGPT
Unpin a memory and re-evaluate its core eligibility.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/plugin_asdk_app_6a5a92a75f0c8191bd481042916a6f7d"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/plugin_asdk_app_6a5a92a75f0c8191bd481042916a6f7d)