Blue Synergy Cortex (v3.0)

MCP serverEverything else

Long-term, drift-free cognitive memory engine for AI Agents and Cursor IDE.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use Blue Synergy Cortex (v3.0)

Install Blue Synergy Cortex (v3.0)

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http blue-synergy-cortex-v3-0 'https://cortex.bluesynergy.io/v1/mcp/sse'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://cortex.bluesynergy.io/v1/mcp/sse

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=blue-synergy-cortex-v3-0&config=eyJ1cmwiOiJodHRwczovL2NvcnRleC5ibHVlc3luZXJneS5pby92MS9tY3Avc3NlIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://cortex.bluesynergy.io/v1/mcp/sse

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add blue-synergy-cortex-v3-0 --url 'https://cortex.bluesynergy.io/v1/mcp/sse'

    Run it once, then sign in with codex mcp login blue-synergy-cortex-v3-0 if the server asks for an account.

From the project's README

As published by novotapeter-bs/bs_cortex in README.md.

Long-term, drift-free cognitive memory engine for AI Agents, Cursor IDE, and Claude Desktop via Model Context Protocol (MCP).


Stop AI Amnesia & Specification Drift

Blue Synergy Cortex implements an enterprise-grade Tri-Stream Architecture backed by transactional PostgreSQL and Neo4j:

  1. User Stream: Generalizes conversational habits and user preferences over time.
  2. Identity Stream: Deterministic guardrails and behavioral axioms that prevent sycophancy.
  3. Knowledge Stream (Living Specs): Exact architecture specifications, hardware limits, and system parameters organized into an immutable Universal Scientific Ontology. This stream is protected against lossy compression, semantic decay, and accidental drift.

Quickstart (1 Minute Setup)

To use Cortex, you need an API key. 👉 Get your 21-day Free Trial API Key here

1. Cursor IDE Integration

  1. Open Cursor Settings (Ctrl+Shift+J or Cmd+Shift+J).
  2. Navigate to Features -> MCP Servers -> Add new MCP server.
  3. Configure as follows:
    • Name: cortex-memory
    • Type: sse
    • URL: https://cortex.bluesynergy.io/v1/mcp/sse?api_key=YOUR_API_KEY
  4. Save. Your Cursor Composer and Agent now have permanent recall across restarts!

2. Claude Desktop Integration

Edit your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

AAdd the Cortex remote configuration (Claude Desktop):

{
  "mcpServers": {
    "cortex": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cortex.bluesynergy.io/v1/mcp/sse",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}

Restart Claude Desktop


3. Other MCP Clients (Windsurf, VS Code Cline, Roo Code, Zed, Cursor)

Use the SSE endpoint directly in your tool's MCP configuration:

{
  "mcpServers": {
    "cortex": {
      "url": "https://cortex.bluesynergy.io/v1/mcp/sse?api_key=ctx_live_..."
    }
  }
}

4. Custom Agents & REST API (LangChain, CrewAI, AutoGen, OpenAI Custom GPTs, LlamaIndex, n8n)

Integrate Cortex directly into your custom pipelines via our sub-65ms REST endpoints:

Example: Querying Context (cURL)

curl -X POST https://cortex.bluesynergy.io/v1/recall \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "System database requirements",
    "user_id": "developer",
    "agent_id": "backend_agent"
  }'

Available MCP Tools

Once connected, your AI agent automatically acquires these native tools:

Tool NameTypeDescription
cortex_recallQuerySub-65ms semantic & graph recall. Injects user bio, active project specs, and knowledge graph relations before generating a response. Always active (even in read-only mode).
cortex_ingest_turnIngestionMandatory turn logger. Automatically captures the conversational turn (user_message + assistant_message) into the async ingestion buffer for nocturnal consolidation.
cortex_store_memoryWriteExplicitly saves system constraints, architectural decisions, and project facts directly to a specific project_id and topic.
cortex_get_project_specInspectionDeterministically retrieves the full canonical specification (Living Document) for any project, bypassing vector search limitations.
cortex_triage_generalMaintenanceCompaction and migration tool that moves unstructured notes from the general incubator into dedicated projects.

Core Architecture Highlights

  • Sub-65ms Zero-LLM Recall: Direct exact-cosine edge matching in Neo4j and indexed PostgreSQL vectors—bypassing heavy runtime LLM keyword extractors.
  • Dual-Zone Fast-Append: Instant raw fact capture (< 20ms) into an inbox zone, followed by asynchronous consolidation into a structured scientific schema (Summary, Aim, Materials & Methods, Ideas, Attachments).
  • Anti-Race Synthesis Guard: Invariant guard enforcing facts_volume_ratio >= 0.85, preventing critical parameter deletions during re-indexing.
  • Immunity Shield: Operational errors, tool crashes, and conversational apologies are filtered by design and never corrupted into permanent memory.

Support & Feedback

Encountered an issue or have a feature suggestion?

Advanced
Delivery
cortex MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-novotapeter-bs-cortex
Source
github.com/novotapeter-bs/bs_cortex
Hosted endpoint
https://cortex.bluesynergy.io/v1/mcp/sse