CF Memory Plugin

Persistent memory for AI agents, backed by Cloudflare Agent Memory.

This plugin is a thin client. Cloudflare stores, classifies, and recalls memories. You do not run a vector DB, embeddings pipeline, or Worker.

Private beta. Paid Workers is required. Paid Workers alone is not enough — you still need Agent Memory entitlement.

60-second setup

pip install git+https://github.com/hansakoch/cf-memory-plugin.git

export MCP_CLOUDFLARE_API_KEY="cf-api-token-with-agent-memory"
export CF_ACCOUNT_ID="your-32-char-account-id"

cf-memory test

CF_ACCOUNT_ID is required. There is no default account. Find it in the Cloudflare dashboard sidebar.

Create the token at dash.cloudflare.com/profile/api-tokens with Agent Memory permission only. Do not reuse a Global API Key.

Related MCP server: agentram-mcp

What this is

Cost

Recommended: Workers Paid on the account that will hold memory. Do not put production memory on a free account. Do not assume every paid Workers account has Agent Memory — we verified paid ≠ entitlement.

After beta, treat Agent Memory as a separate bill. Cloudflare has not published GA rates yet.

Dependencies

Runtime:

Optional:

No Cloudflare Worker, Wrangler, D1, Vectorize, or Workers AI binding is required for this plugin. Those are Cloudflare products this client does not use.

Security

Follow Cloudflare's token rules: API token best practices.

• Store MCP_CLOUDFLARE_API_KEY in the environment or a secret store. Never commit it.

• Scope the token to Agent Memory on one account.

• Set CF_ACCOUNT_ID yourself. This plugin will not fall back to another account.

• cf-memory a2a binds to 127.0.0.1 by default. Do not expose it to the public internet without auth.

• ingest and sync_turn send conversation text to Cloudflare. Do not ingest secrets, passwords, or customer PII you are not allowed to store.

• Use one namespace per app and one profile per user/tenant.

• Rotate the token from the API Tokens page if it leaks.

See SECURITY.md.

Use it from an agent

Same MCP block everywhere. Only the config file path changes.

{
  "mcpServers": {
    "cf-memory": {
      "command": "cf-memory",
      "args": ["serve"],
      "env": {
        "MCP_CLOUDFLARE_API_KEY": "your-token",
        "CF_ACCOUNT_ID": "your-account-id"
      }
    }
  }
}

Hermes is the only native provider. It prefetches in the background so recall does not add ~5s to every turn.

hermes config set memory.provider cloudflare-memory
hermes cloudflare-memory test

Python:

import asyncio
from cloudflare_memory import CloudflareMemoryClient

async def main():
    async with CloudflareMemoryClient(
        account_id="your-account-id",
        api_token="your-token",
        namespace="my-app",
        profile="default",
    ) as client:
        await client.remember("User prefers concise answers.")
        result = await client.recall("How should I answer?")
        print(result.answer)

asyncio.run(main())

CLI

cf-memory test                          # connectivity
cf-memory serve                         # MCP (stdio)
cf-memory a2a --port 9120               # A2A on localhost
cf-memory card                          # print agent card

hermes cloudflare-memory status
hermes cloudflare-memory namespaces

Deploy the landing page (optional)

The plugin itself is not a Worker. The public page at cloudflare-memory.pages.dev is a static Cloudflare Pages site.

# token needs Pages:Edit on the same account
export CLOUDFLARE_API_TOKEN=...
export CLOUDFLARE_ACCOUNT_ID=...
npx wrangler pages deploy ./public --project-name cf-memory-plugin

Pages docs · Wrangler

Credits

• Memory backend: Cloudflare Agent Memory (blog, Discord, Community)

• Protocol: Model Context Protocol

• Hermes provider contract: Nous Research Hermes Agent

• HTTP client: httpx

This repo is not affiliated with Cloudflare or Nous Research.

License

MIT