How to Use the Deno Deploy MCP in LangChain

Q: How do I create a new Deno Deploy deployment with a LangChain agent?

Your agent calls the createdeployment tool with the app ID and necessary files. Since LangChain can chain commands, you can have it first call listapps to find the right ID, creating a multi-step, self-correcting pipeline.

Q: Can I stream build logs from Deno Deploy in my LangChain app?

Yes, the getbuildlogs and getrevisionprogress tools are stream-enabled. In LangChain, this means your agent can get real-time feedback from Deno Deploy as a build is happening, allowing it to react instantly to issues.

Q: How does my LangChain agent list all Deno Deploy applications?

It just calls the listapps tool. The tool supports pagination, so your agent can automatically fetch all pages to get a complete list of every application in your Deno Deploy organization.

Build Deno Deploy CI/CD pipelines that your LangChain agents can run on their own.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deno Deploy MCP to LangChain

Create your Vinkius account to connect Deno Deploy to LangChain 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 Deno Deploy with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain together deployment workflows

This MCP Server gives your agent the tools to manage Deno Deploy applications from start to finish. A single chain can create a new application with `create_app`, push a new version using `create_deployment`, and then monitor its progress with `get_revision_progress`. Because LangChain treats each tool call as a link in a chain, the output of one step feeds directly into the next. Your agent can get the new revision ID from `create_deployment` and immediately use it to stream build logs with `get_build_logs`. It’s a completely autonomous deployment process.

Automate infrastructure audits

Give your agent a task like, "Audit our Deno Deploy setup." It can start by getting a full picture with `list_apps` and `list_projects`. From there, it can dig into each application, checking its deployment history with `list_revisions`. This isn't just about listing things. Your agent can build logic around the data. For instance, it can check which apps are using outdated layers with `get_app` and `update_layer`, or find projects that don't have a custom domain assigned via `list_domains`.

Build intelligent monitoring agents with this MCP Server

Your agent can watch over your applications by periodically calling `get_app_logs`. You define the task, and the agent handles the execution. It can parse the logs, look for specific error patterns, and decide on the next action. If it finds a critical error, the agent can use its other tools to gather more context. It could grab the specific revision details with `get_revision` to see what changed, or get organization info with `get_organization` to notify the right team. This is active monitoring, not just passive log scraping.

Setup guide

Set up Deno Deploy MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Deno Deploy tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "deno-deploy-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Deno Deploy transactions"
    })
    print(result["messages"][-1].content)

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 Deno Deploy. 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 Deno Deploy 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 Deno Deploy MCP in LangChain

Your agent calls the `create_deployment` tool with the app ID and necessary files. Since LangChain can chain commands, you can have it first call `list_apps` to find the right ID, creating a multi-step, self-correcting pipeline.

Yes, the `get_build_logs` and `get_revision_progress` tools are stream-enabled. In LangChain, this means your agent can get real-time feedback from Deno Deploy as a build is happening, allowing it to react instantly to issues.

This server standardizes the toolset. You get pre-built, typed tools that plug right into your agent executor without writing custom wrappers. Vinkius also handles authentication and infrastructure, so you just pass the tools to your agent.

It just calls the `list_apps` tool. The tool supports pagination, so your agent can automatically fetch all pages to get a complete list of every application in your Deno Deploy organization.

Your agent only touches the Deno Deploy data it needs for a specific tool call, like app names, logs, and deployment metadata. Every request runs in a V8 Isolate sandbox on our zero-trust network. Vinkius handles the auth token, and we never store your Deno Deploy data.

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