x=hub

your toolset

    build deployment
    sign in

    Blue Synergy Cortex

    mcpother
    io.github.novotapeter-bs/cortex · v1.0.0
    deploy just this

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

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
    # once, as root:
    docker build -t mcp-local/cortex:latest https://github.com/novotapeter-bs/bs_cortex.git
    
    #!/usr/bin/env bash
    # cortex (io.github.novotapeter-bs/cortex), recipe docker (generated).
    # Generated by Hub for toolset "my-agent"; started by mcp-my-agent-cortex.service.
    set -euo pipefail
    export HOST=127.0.0.1 PORT=8101
    exec docker run --rm --name mcp-my-agent-cortex -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env mcp-local/cortex:latest
    
    [Unit]
    Description=MCP server cortex (toolset my-agent), generated by Hub
    After=network-online.target docker.service
    Wants=network-online.target
    
    [Service]
    Type=simple
    User=mcp
    Group=mcp
    SupplementaryGroups=docker
    EnvironmentFile=/etc/mcp/my-agent.env
    Environment=HOME=/var/lib/mcp/cortex
    WorkingDirectory=/var/lib/mcp/cortex
    ExecStart=/opt/mcp/my-agent/bin/cortex.sh
    Restart=on-failure
    RestartSec=5
    NoNewPrivileges=true
    ProtectSystem=strict
    ProtectHome=true
    PrivateTmp=true
    ReadWritePaths=/var/lib/mcp/cortex
    
    [Install]
    WantedBy=multi-user.target
    
    generated from the record, not tested yet
    CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
    docker build -t cortex https://github.com/novotapeter-bs/bs_cortex.git
    docker run --rm -p 127.0.0.1:8101:8000 cortex
    
    generated from the record, not tested yet
    CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
    # Generated by Hub for toolset "my-agent" (2026-10-18T04:40:27+00:00).
    # Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
    #   cp .env.example .env    # fill the ${VAR}s
    #   docker compose up -d && bash smoke.sh
    # Remote servers are not here: clients reach them directly (see clients/).
    name: mcp-my-agent
    services:
      cortex:
        build:
          context: https://github.com/novotapeter-bs/bs_cortex.git
        ports:
        - 127.0.0.1:8101:8000
        restart: unless-stopped
        x-note: 'CHANGE_ME: built from the repository''s Dockerfile, assuming it serves streamable HTTP at
          :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.'
    volumes:
      npm-cache: {}
      uv-cache: {}
    
    generated from the record, not tested yet
    CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
    # Generated by Hub for toolset "my-agent" (2026-10-18T04:40:27+00:00).
    #   kubectl create namespace mcp
    #   kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
    #   kubectl apply -f kubernetes.yaml
    # Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
    # with auth in front before exposing any of them.
    apiVersion: v1
    kind: Namespace
    metadata:
      name: mcp
    ---
    apiVersion: apps/v1
    kind: Deployment
    metadata:
      name: cortex
      namespace: mcp
      labels: &id001
        app: cortex
    spec:
      replicas: 1
      selector:
        matchLabels: *id001
      template:
        metadata:
          labels: *id001
        spec:
          containers:
          - name: cortex
            image: CHANGE_ME
            ports:
            - containerPort: 8000
              name: http
            env: []
    ---
    apiVersion: v1
    kind: Service
    metadata:
      name: cortex
      namespace: mcp
    spec:
      selector:
        app: cortex
      ports:
      - port: 8000
        targetPort: http
        name: http
    
    generated from the record, not tested yet
    CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
    # Generated by Hub for toolset "my-agent" (2026-10-18T04:40:27+00:00).
    # Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
    # Each server under `servers` is one Deployment + Service; the keys after it configure
    # upstream charts a worker verified.
    servers:
      cortex:
        enabled: true
        replicas: 1
        port: 8000
        path: /mcp
        container:
          name: cortex
          image: CHANGE_ME
          ports:
          - containerPort: 8000
            name: http
          env: []
    
    # helm install my-agent helm/my-agent -n mcp
    

    in the cloud

    one click: the provider's deploy form opens filled in, in your own account
    koyeb

    Koyeb builds the repository's Dockerfile from branch main; change the branch in the form if the default one has another name.

    Clients connect to the service's https://…koyeb.app address plus /mcp.

    cloud run

    Cloud Shell clones the repository, builds its Dockerfile and deploys it to Cloud Run.

    Cloud Run sends requests to $PORT (8080); the recipe expects :8000, so the server has to read PORT, or set the container port on the service afterwards.

    connect to it

    copy what your client needs
    {
      "mcpServers": {
        "cortex": {
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    #!/usr/bin/env bash
    # Registers every server with Claude Code (run once; `claude mcp list` to check).
    set -euo pipefail
    set -a; [ -f .env ] && source .env; set +a
    claude mcp add cortex -- CHANGE_ME
    
    {
      "mcpServers": {
        "cortex": {
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    {
      "servers": {
        "cortex": {
          "type": "stdio",
          "command": "CHANGE_ME",
          "args": []
        }
      }
    }
    name: my-agent
    target: local
    servers:
    - hub: io.github.novotapeter-bs/cortex
    
    • no recipe for target 'local': fill the files by hand

    tools · 8

    • cortex_consolidate_projectDvoufázová asynchronní konsolidace projektu: bezpečně zařadí projekt do fronty pro stažení střípků (I. řád) a syntézu II. řádu s Anti-Drift Guardem.

      Dvoufázová asynchronní konsolidace projektu: bezpečně zařadí projekt do fronty pro stažení střípků (I. řád) a syntézu II. řádu s Anti-Drift Guardem.

      pin 491176870f57cab430c97bf08b0a63ca67c141f8f5d158035391df53df72b9c5
    • cortex_create_projectExplicitní založení a autorizace nového projektu uživatelem. Umožní ukládat data pod daný project_id a adoptuje případné související poznámky z general.

      Explicitní založení a autorizace nového projektu uživatelem. Umožní ukládat data pod daný project_id a adoptuje případné související poznámky z general.

      pin 402b7b91eb47940978ceada15520b20c5d4915d85f8cba51f510a71b8177ae6f
    • cortex_get_project_specDeterministické přečtení živé kanonické specifikace projektu (Living Spec).

      Deterministické přečtení živé kanonické specifikace projektu (Living Spec).

      pin 54de9f40a6d4d5930155a852f8d32de1221cb1379c831c7e3d82d9c8a084a702
    • cortex_ingest_turnMANDATORNÍ PO KAŽDÉ ODPOVĚDI: Zaznamená aktuální tah konverzace do kognitivního bufferu Cortexu s volitelným směrováním k projektu.

      MANDATORNÍ PO KAŽDÉ ODPOVĚDI: Zaznamená aktuální tah konverzace do kognitivního bufferu Cortexu s volitelným směrováním k projektu.

      pin 8bfde33f8fb5ace93fea52954a9dc1a6b24240d6ae2e56d1b9f54392a5a9f3e6
    • cortex_manage_draftSpráva draftu projektu v karanténě: schválení do ostrého provozu ('approve') nebo kompletní smazání omylu ('reject').

      Správa draftu projektu v karanténě: schválení do ostrého provozu ('approve') nebo kompletní smazání omylu ('reject').

      pin a418eb952d46dd4f012d40060a9ac2607cf6743ba8981ca5c2b72dc45f9d3a8b
    • cortex_recallSémantické vyhledání v dlouhodobé paměti Cortexu. Podporuje volitelný kompaktní režim pro CLI agenty.

      Sémantické vyhledání v dlouhodobé paměti Cortexu. Podporuje volitelný kompaktní režim pro CLI agenty.

      pin c2b6cea9d1a920e34cb28cbd1ad4e7415c775548bb57f8d6a275aa1705aa8d1d
    • cortex_store_memoryTrvalé uložení projektové specifikace, faktu nebo architektury pod konkrétní project_id a téma.

      Trvalé uložení projektové specifikace, faktu nebo architektury pod konkrétní project_id a téma.

      pin 20a5d7514cbee17eb311ab3fcfa31c715714aaa65a5c9146958bda8d1de819c4
    • cortex_triage_generalAsistovaný úklid a přesun střípků z obecného inkubátoru (general) do schválených projektů.

      Asistovaný úklid a přesun střípků z obecného inkubátoru (general) do schválených projektů.

      pin 336d6462c5ce8ffb2c5eecda923b559539454c26442ae2cc0e589ff99b541c9c

    runs · 1

    the latest tests of this entry by the hub and its workers, newest first
    dateworkermethodstatussandboxreason
    2026-10-16 09:44 local-mac remotemcp 2025-11-25 ok8 tools none —