How to Use the Medium MCP in Mastra AI

Q: How does Mastra AI determine which publication to use on Medium?

Your agent calls listpublications to get a list of valid publication IDs. It then selects the correct ID based on the topic of the article and passes it to createpublicationpost.

Automate your entire multi-step publication workflow with Mastra AI and the Medium integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Medium MCP to Mastra AI

Create your Vinkius account to connect Medium to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Medium with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step publishing pipelines in Mastra AI

This MCP Server uses `create_draft` as the core step inside your Mastra AI workflow to automate content distribution. If an engineering update triggers your Mastra workflow, the agent automatically drafts a summary and queues it for your editorial team on Medium. The pipeline handles API errors gracefully by running Mastra AI's built-in retry logic during a `create_post` run. Should Medium's rate limits be reached, the Mastra workflow pauses, backs off exponentially, and retries the submission without crashing your automation.

Route content to publications with Mastra AI

The `list_my_publications` tool allows your Mastra AI workflow engine to scan your available target publications before executing a run. By evaluating the article's topic, the agent matches it to the best publication ID and calls `create_publication_post` automatically. Verification is handled by Mastra AI using `list_contributors` to confirm the author has the correct publication access. If the check fails, the Mastra workflow branches conditionally, routing the post to a personal draft via `create_post` instead.

Verify credentials inside Mastra AI agents

The `get_my_user_id` tool serves as the initial validation step for any Mastra AI agent running scheduled content tasks. Matching this ID against your internal database ensures the executing agent is writing to the correct writer's account. User profiles are kept in sync across runs using `get_my_profile` to update your Mastra AI database. This prevents identity mismatches and guarantees that automated posts are always attributed to the correct Medium author.

Setup guide

Set up Medium MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Medium tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "medium-mcp-client",
  servers: {
    "medium-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Medium Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Medium tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Medium transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Medium. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Medium now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Medium MCP in Mastra AI

Initialize the client using the Mastra MCP client package and pass the server URL. You can then spread the tools returned by `listTools` directly into your agent configuration.

Yes, you can configure Mastra's workflow engine to pause before executing `create_public_post`. The agent will generate the content, wait for your manual approval, and then proceed with the live publish.

Your agent calls `list_publications` to get a list of valid publication IDs. It then selects the correct ID based on the topic of the article and passes it to `create_publication_post`.

Mastra's workflow engine catches the error and applies your defined retry policy. If the API remains unresponsive, the agent can escalate the issue by saving the content as a local backup.

Your API token is injected into the server environment at runtime and never exposed to the agent's LLM context. The server processes your draft text and publication IDs through secure V8 sandboxes that wipe all data immediately after execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript