Quick start

Get memco working in one real project.

Your code stays local. Only query text, insights you explicitly share and feedback cross the boundary.

Connect memco over MCP to the agent you already use, search shared memory before you code, and save what worked for the next agent.

Walk through the four steps Open full docs
  • About three minutes to connect
  • No repository upload
  • Personal and team workspaces
Claude Code
/plugin marketplace add memcoai/marketplace /plugin install shared-memory@memco
Codex
$ codex plugin marketplace add memcoai/marketplace $ codex plugin add shared-memory@memco
Cursor
https://spark.memco.ai/mcp — Cursor connects through the UI — Settings → Plugins → Import from Repo, or paste this endpoint into .cursor/mcp.json.
Claude Desktop
Memco Shared Memory — In Claude Desktop or claude.ai, open Settings → Connectors, find Memco Shared Memory in the directory and connect. You sign in with your memco account.

Quick-start steps

Step 1 of 4

  1. 01Account
  2. 02Connect
  3. 03Verify
  4. 04Use it

01Account

1. Create your memco account.

The one prerequisite. Everything after this is a connection, not a code change — most people never install anything.

Create your account Read this in the docs

02Connect

2. Connect your agent.

Install the marketplace plugin, or point any MCP-compatible client at the endpoint. Pick the client you actually use.

  • Claude CodePlugin marketplace — recommended

    /plugin marketplace add memcoai/marketplace
    /plugin install shared-memory@memco
    Run both inside Claude Code.

    Or add the MCP server directly
    claude mcp add memco-shared-memory --transport streamable-http https://spark.memco.ai/mcp
  • CodexPlugin marketplace — recommended

    codex plugin marketplace add memcoai/marketplace
    codex plugin add shared-memory@memco
    Or run codex and open /plugins to browse and install interactively.

  • CursorPlugin marketplace — recommended
    Or configure the MCP server directly — .cursor/mcp.json
    { "mcpServers": { "memco-shared-memory": { "url": "https://spark.memco.ai/mcp" } } }
    • Dashboard → Settings → Plugins
    • Team Marketplaces → Add Marketplace → Import from Repo
    • Point to memcoai/marketplace
    • Reload Cursor — Developer: Reload Window
    • Install memco-shared-memory from the marketplace panel
  • Claude DesktopConnector directory — recommended
    Or configure the MCP server manually — claude_desktop_config.json
    { "mcpServers": { "memco-shared-memory": { "url": "https://spark.memco.ai/mcp" } } }
    • Settings → Connectors
    • Find Memco Shared Memory in the directory
    • Connect and sign in with your memco account
  • Endpoint and auth

    Authentication uses OAuth — you sign in with your memco dashboard account when the client first connects. API keys are available as an alternative.

    memco MCP endpoint
    https://spark.memco.ai/mcp
  • Using a client that isn’t listed?

    In ChatGPT, install the Memco Shared Memory plugin from the plugin directory.

    Anything that speaks MCP can use the same endpoint. Add it as a streamable-HTTP server in whatever config that client uses, then restart it — most clients only scan MCP configuration at launch. See the marketplace repo.

shared-memory@memco connects memco Shared Memory. Personal memory is a separate plugin, personal-memory@memco, or the MCP server at https://spark.memco.ai/mcp-personal.

03Verify

3. Check the connection.

Ask the agent directly. A live connection lists the domains your account can reach.

What memco domains do I have access to?
Two domains, kept as separate stores — a repository fix never surfaces in a client-reporting search.
Expected response
coding · knowledge

04Use it

4. Search, then contribute.

Two things the agent can do now that it could not before. The second one is what makes the first one better next week.

  • Search

    Search memco for best practices on error handling in this codebase

  • Contribute

    Save this as an insight in memco — the payments service requires idempotency keys on all POST requests

Share the insight and the reasoning. Do not paste source code, secrets, credentials or private repository details.

The loop

The first run solves the task. The next run inherits the insight.

  1. 01Agent A queries
  2. 02Work happens locally
  3. 03Distilled insight is shared
  4. 04Agent B queries
  5. 05Feedback improves ranking

Separate scopes with separate boundaries — never the same store.

  • Stays on the device
    • Repository
    • Source files
    • Environment & secrets
    • Git history
  • The repository never crosses this lineCrosses only through an explicit action
    • Query text
    • Insight title, content & tags
    • Feedback on a recommendation
  • Personal workspace

    Your private memory

  • Private team

    Your team’s private memory

Hands-on

Try the loop in a safe project.

The memco tutorial is a small Python project with a deliberate piece of tribal knowledge. Use it to watch one agent inherit a solution another agent had to discover.

  1. 01
    Open the project and task.py in the coding agent.
  2. 02
    Ask the agent to implement solve_task.
  3. 03
    Let memco search for the missing insight.
  4. 04
    Confirm the result and allow feedback to close the loop.

Four moves

Privacy

Your repository is not the payload.

RowStays localSent only through an explicit action
Source files and codebaseQuery text
File paths and directory structureInsight title, content and tags
Environment variables and secretsFeedback on a recommendation
Git history and diffs
Configuration and lock files
Read the full privacy model
  1. memco does not read the filesystem automatically. Text you paste into a query or insight is transmitted, so do not paste secrets or sensitive repository details.
  2. Every workspace has its own memory boundary, and a personal one works exactly like a team one. Nothing you write leaves it.

Next steps

One agent learns. The next starts ahead.

Start with memco Set up a private team workspace Full documentation Public and open-source workflows Private-team setup