Koskamo

Memlo MCP

Memlo is a hosted memory service for AI agents that allows saving and searching short notes called memories. It enables one person's memories to work across all their agents and apps, reducing token usage compared to file-based memory.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Memlo MCP logo, by MemloVendor evidenceStreamable HTTPOAuth sign-inEndpoint checked 2026-11-01Operated by Memlo
You need:Before you start: an account
MCP endpoint (Streamable HTTP)
https://memlo.ai/mcp
Vendor documentation

What you can do with it

  • Save short notes as memories
  • Search memories across agents
  • Share memory between agents
  • Reduce agent token usage

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: ai.memlo/memlo@1.0.0Project website

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
60 ms
95th percentile latency
60 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 60 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http memlo-mcp https://memlo.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add memlo-mcp --url https://memlo.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable memlo-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "memlo-mcp": {
      "url": "https://memlo.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "memlo-mcp": {
      "type": "streamableHttp",
      "url": "https://memlo.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start memlo-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "memlo-mcp": {
      "type": "http",
      "url": "https://memlo.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http memlo-mcp https://memlo.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "memlo-mcp": {
      "url": "https://memlo.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "memlo-mcp": {
      "serverUrl": "https://memlo.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Memlo MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,975

Do you run Memlo MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing