How to Use the DevDocs MCP in Mastra AI

Q: How do I initialize the DevDocs MCP Server in Mastra AI?

Install @mastra/mcp@latest. Create a new MCPClient instance with your server ID and endpoint URL, then spread mcpClient.listTools() into your agent's tool array.

Wire up automated documentation retrieval pipelines with Mastra AI and handle missing framework queries gracefully.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevDocs MCP to Mastra AI

Create your Vinkius account to connect DevDocs 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 DevDocs with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mastra AI MCP Server Branching Logic

The `list_libraries` tool checks if a specific language actually exists on DevDocs before your workflow attempts to read from it. You configure a conditional branch in Mastra AI to halt the pipeline if the requested SDK is missing. This stops downstream errors cold. The agent verifies the target upfront, then executes the correct path based on that boolean result.

Resilient Index Searching

The `search_docs` tool in this MCP Server hunts down specific manual pages within a given library. If the DevDocs API drops your request, Mastra catches the failure and triggers an exponential backoff retry. Your agent won't crash over a network blip. The framework swallows the error and tries again while your pipeline holds position.

Approval-Gated Markdown Extraction

The `read_page` tool pulls massive Markdown files directly into your workflow's memory. Because these files consume heavy token counts, you wrap this step in a `requireToolApproval` flag. A human reviews the target path before the agent dumps 15,000 tokens of text into the context window. You keep your API costs strictly under control.

Setup guide

Set up DevDocs 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 DevDocs 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: "devdocs-mcp-client",
  servers: {
    "devdocs-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent DevDocs 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 DevDocs. 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 DevDocs 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 DevDocs MCP in Mastra AI

Install `@mastra/mcp@latest`. Create a new `MCPClient` instance with your server ID and endpoint URL, then spread `mcpClient.listTools()` into your agent's tool array.

The built-in workflow engine catches HTTP timeouts from the search index. It applies exponential backoff and retries the query without requiring custom error-handling code.

You check the library list first. If the framework exists, the workflow proceeds to search. If it fails, the workflow branches to notify the user instead of throwing an exception.

The client auto-detects between Streamable HTTP or SSE based on the endpoint. You just pass the URL and let the framework negotiate the connection.

The system processes your specific API search strings and requested page targets inside an ephemeral execution environment. Once the workflow extracts the Markdown, the sandbox terminates completely. Nobody retains your pipeline's research history.

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