Do I still need embeddings or a vector database?

Not for the registry. Pages are curated and small enough to read whole. The agent picks pages by title and use-when instruction, which is more predictable than similarity search for policy content.

Does Memrio need a workspace or page-set header?

No. The API key is scoped to one workspace and one agent page set, so the key alone tells the server what the agent may read. Send only the Authorization header.

Which pages can the agent see?

Only published pages inside the agent page set you configured. Drafts and pages waiting on review are hidden unless you turn on "Read drafts" for a test agent.

Can the agent edit pages?

Only if you enable "Can edit pages" on that agent. It then gets get_page_source, create_page, update_page, and append_to_page. Edits are submitted as versions for human review unless the agent is also allowed to publish.

memrio

OpenAI · Agent frameworks

Memrio for the OpenAI Agents SDK

Building agents on the OpenAI Agents SDK? Attach the registry as an MCP server and your agent inherits a governed page set with no retrieval pipeline to maintain. Python and TypeScript both work.

Jump to setup

live

OpenAI Agents SDKmemrio

Why pair them

Skip the RAG pipeline

No chunking, no vector store to babysit. The agent browses titles and use-when instructions, then opens whole pages.

Governance lives outside the code

Product and ops teams edit pages and approve changes. Your agent code never redeploys for a policy update.

Instructions travel with content

Critical instruction blocks arrive inside get_page so the model applies rules where they matter.

Setup

2 steps, about ten minutes.

You need two values from an agent page in Memrio: the workspace MCP URL and an API key. Examples use https://memrio.ai/api/mcp/acme — swap in yours.

Create an agent and key first

Python — connect over Streamable HTTP

Pass the URL and Authorization header in params. The server handles session setup.

agent.py

from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    async with MCPServerStreamableHttp(
        name="memrio",
        params={
            "url": "https://memrio.ai/api/mcp/acme",
            "headers": {"Authorization": "Bearer mr_live_8f3a…"},
        },
    ) as registry:
        agent = Agent(
            name="Support",
            instructions=(
                "Browse the memrio page set first. "
                "Answer only from the pages you open."
            ),
            mcp_servers=[registry],
        )
        result = await Runner.run(agent, "What is our refund window?")
        print(result.final_output)

TypeScript — hosted MCP tool

Let the Responses API call the registry directly so tool round-trips never leave OpenAI’s side.

agent.ts

import { Agent, hostedMcpTool, run } from '@openai/agents';

const agent = new Agent({
  name: 'Support',
  instructions:
    'Browse the memrio page set first. Answer only from the pages you open.',
  tools: [
    hostedMcpTool({
      serverLabel: 'memrio',
      serverUrl: 'https://memrio.ai/api/mcp/acme',
      headers: { Authorization: 'Bearer mr_live_8f3a…' },
      requireApproval: 'never',
    }),
  ],
});

const result = await run(agent, 'What is our refund window?');
console.log(result.finalOutput);

Try it

A first prompt for OpenAI Agents SDK

“What is our refund window for annual plans?”

FAQ

OpenAI Agents SDK and Memrio

Do I still need embeddings or a vector database?: Not for the registry. Pages are curated and small enough to read whole. The agent picks pages by title and use-when instruction, which is more predictable than similarity search for policy content.
Does Memrio need a workspace or page-set header?: No. The API key is scoped to one workspace and one agent page set, so the key alone tells the server what the agent may read. Send only the Authorization header.
Which pages can the agent see?: Only published pages inside the agent page set you configured. Drafts and pages waiting on review are hidden unless you turn on "Read drafts" for a test agent.
Can the agent edit pages?: Only if you enable "Can edit pages" on that agent. It then gets get_page_source, create_page, update_page, and append_to_page. Edits are submitted as versions for human review unless the agent is also allowed to publish.

Other integrations