Omega Memory MCP Server

AI coding agents are stateless. Every new session starts from zero. The "solutions" either lock you into one model provider or send your codebase

Local serverstdioPython

What is the Omega Memory MCP server?

Omega Memory MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. AI coding agents are stateless. Every new session starts from zero. The "solutions" either lock you into one model provider or send your codebase context to their cloud.

What you get

  • Multi-Agent Coordination — (omega-pro) — File and branch locking, session management, task queues with dependencies, intent broadcasting, and agent-to-agent messaging. 29 coordination tools that prevent agents from overwriting each other's work
  • Intelligent LLM Routing — (omega-pro) — Classifies tasks and routes to the optimal model. Coding → Claude Sonnet. Quick edit → Llama 8b at 1/60th the cost. 1M token context → Gemini Flash. 5 providers, 4 priority modes, sub-2ms intent classification
  • Knowledge Base — (omega-pro) — Ingest PDFs, markdown, web pages, and text files into a searchable knowledge base with semantic chunking
  • Entity Registry — (omega-pro) — Multi-entity corporate memory with relationships, hierarchies, and entity-scoped memories/profiles/documents
  • Secure Profile — (omega-pro) — AES-256 encrypted personal data storage with macOS Keychain integration

What the assistant can call

Once Omega Memory is connected, these are the calls the assistant has available:

  • omega_store — Store typed memory (decision, lesson, error, summary)
  • omega_query — Semantic search with tag filters and contextual re-ranking
  • omega_welcome — Session briefing with recent memories and profile
  • omega_profile — Read or update user profile
  • omega_delete_memory — Delete a specific memory by ID
  • omega_edit_memory — Edit the content of a memory
  • omega_list_preferences — List all stored user preferences
  • omega_health — Detailed health check with memory usage and recommendations
  • omega_backup — Export or import memories for backup/restore
  • omega_lessons — Cross-session lessons ranked by access count
  • omega_feedback — Record feedback on a surfaced memory
  • omega_clear_session — Clear all memories for a specific session

Setting it up

omega-memory on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Omega Memory's toolset — omega_store, omega_query, omega_welcome and 11 more — is a fair guide to whether it matches your workflow. It is maintained by omega-memory; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Omega Memory.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the omega memory mcp server does with a few real requests.

Available tools

ToolWhat it does
omega_storeStore typed memory (decision, lesson, error, summary)
omega_querySemantic search with tag filters and contextual re-ranking
omega_welcomeSession briefing with recent memories and profile
omega_profileRead or update user profile
omega_delete_memoryDelete a specific memory by ID
omega_edit_memoryEdit the content of a memory
omega_list_preferencesList all stored user preferences
omega_healthDetailed health check with memory usage and recommendations
omega_backupExport or import memories for backup/restore
omega_lessonsCross-session lessons ranked by access count
omega_feedbackRecord feedback on a surfaced memory
omega_clear_sessionClear all memories for a specific session
omega_similarFind memories similar to a given one
omega_timelineMemories grouped by day

How to install the Omega Memory MCP server

{
  "mcpServers": {
    "omega-memory": {
      "command": "uvx",
      "args": ["omega-memory"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Omega Memory to omega store.
  • Use Omega Memory to omega query.
  • Use Omega Memory to omega welcome.

Frequently asked questions

It connects Omega Memory to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (omega_store, omega_query, omega_welcome, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Omega Memory directly.