Ratary Memory MCP
Ratary is an AI Brain Platform — infrastructure that gives AI: Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata…
Что умеет
- Save Memory: Create a new persistent coding memory entry with title, markdown body, project scope, and optional tags.
- Update Memory: Update fields on an existing memory by UUID without creating a new record.
- Delete Memory: Permanently delete a memory by UUID. Prefer archive_memory for reversible removal.
Какие данные видит
Нужен ли аккаунт
Не нужен: сервер работает без входа
Ratary is an AI Brain Platform — infrastructure that gives AI:
Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata, relations, graph traversal Intelligent retrieval — hybrid search + bounded context assembly Protocol access — Ratary MCP, REST, optional gRPC It sits between AI clients and storage. One brain, many surfaces — Cursor, Claude Code, custom agents, enterprise APIs, and remote MCP hosts.
The runnable deployment is Ratary Server — this repository. Ratary is the product; Ratary Server is what you clone and run.
Bring your model. Ratary brings the memory.
Список инструментов сервера (28)
Технические названия из tools/list. Нужны только разработчикам.
| save_memory | Create a new persistent coding memory entry with title, markdown body, project scope, and optional tags. |
| update_memory | Update fields on an existing memory by UUID without creating a new record. |
| delete_memory | Permanently delete a memory by UUID. Prefer archive_memory for reversible removal. |
| get_memory | Fetch a single memory by UUID including full content and metadata. |
| get_memory_by_codename | Fetch a memory by stable codename (e.g. AUTH-0001) when UUID is unknown. |
| search_memory | Search memories by keyword, tag, or project using hybrid full-text and semantic ranking. |
| get_memory_by_path | Read a memory by vault source_path when syncing from a file-oriented workflow. |
| get_context | Rank relevant memories and assemble token-budgeted markdown context for a task. |
| build_prompt | Build system and user prompts for an external LLM from ranked project memory. |
| list_projects | List all project slugs that have at least one memory for this owner. |
| list_tags | List distinct tags used across all memories for this owner. |
| link_memories | Create a typed relation edge between two memories in the knowledge graph. |
| list_relations | List graph relations attached to a memory (incoming and outgoing). |
| toggle_favorite | Toggle the favorite flag on a memory for quick access and ranking. |
| archive_memory | Soft-archive a memory so it is hidden from default search but recoverable. |
| get_graph_capabilities | Describe available knowledge-graph traversal modes, limits, and relation types. |
| traverse_relations | Traverse memory relations via bidirectional BFS from a seed memory or slug. |
| list_workspaces | List workspaces owned by the authenticated identity. |
| list_agents | List agent identities registered in the current workspace. |
| register_agent | Register a new agent identity (Cursor, Claude Code, etc.) in the workspace. |
| get_capabilities | Return the deployment capability manifest: enabled modules, tool registry, and limits. |
| negotiate_capabilities | Handshake to verify client-required capability flags against this deployment. |
| submit_signal | Submit memory quality feedback or forge inspection outcome signals for learning loops. |
| run_stewardship | Run the memory stewardship pipeline (dedupe, archive candidates). Dry-run by default. |
| get_compression_status | Report semantic compression status and pending duplicate clusters for the owner. |
| sync_pull | Pull memory deltas from the server since the last sync cursor for a client platform. |
| sync_push | Push batched memory create/update/delete operations from a client platform. |
| sync_status | Get multi-client sync status and last cursor for a platform. |