How to Use the Fastly MCP in LangChain

Q: How do I pass Fastly MCP Server tools to a LangChain agent?

You install the langchain-mcp-adapters package and initialize the server client with your Vinkius endpoint. From there, call gettools() to retrieve tools like listservices and pass them directly to your agent constructor.

Q: Can I inspect CDN traffic stats inside my chain?

Yes, you call getservicestats to fetch real-time traffic volume. This allows your agent to delay deployments if traffic is currently too high.

Run multi-step LangChain chains that audit edge configurations, swap backends, and activate Fastly service versions on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fastly MCP to LangChain

Create your Vinkius account to connect Fastly 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 Fastly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step Fastly deployment chains in LangChain

Connect your LangChain agents directly to your CDN control plane without writing custom API wrappers. By using this MCP Server, your agent inspects active routing setups using `list_services` and inspects specific backends via `list_version_backends` before making any modifications. If a release fails health checks, your chain automatically falls back to a working state. The agent handles the recovery sequence by calling `activate_service_version` to roll back to the last known stable configuration version instantly.

Automate edge cache invalidation after deployments

Keep your LangChain pipelines fast and fresh by linking cache clearing directly to your deployment steps. When your agent detects a successful version rollout, it triggers a global purge using `purge_all_cache` to ensure users see the updates immediately. Trace the entire sequence in LangSmith to monitor latency and token costs. This MCP tool lets you see exactly when and why your agent decided to clear the edge cache for a service.

Audit service configurations and backends dynamically

Your LangChain agent runs deep structural checks across your CDN infrastructure before pushing changes. The agent pulls active domains with `list_version_domains` and cross-references them against your internal system records to catch routing conflicts early. Instead of manual dashboard checks, you get a repeatable reasoning loop. Your agent checks `get_service_stats` to verify traffic levels before calling `delete_service` on decommissioned configurations.

Setup guide

Set up Fastly 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 Fastly 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({
    "fastly-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 Fastly 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 Fastly. 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 Fastly 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 Fastly MCP in LangChain

You install the `langchain-mcp-adapters` package and initialize the server client with your Vinkius endpoint. From there, call `get_tools()` to retrieve tools like `list_services` and pass them directly to your agent constructor.

Yes, you can design a ReAct agent that checks backend status first. If your tests return errors, the chain calls `activate_service_version` to restore the previous stable release.

Your LangChain run loops should use exponential backoff when calling tools like `purge_all_cache`. Vinkius handles the underlying connection, but your chain must handle API rate limit responses gracefully.

Yes, you call `get_service_stats` to fetch real-time traffic volume. This allows your agent to delay deployments if traffic is currently too high.

Your Fastly API tokens are stored in Vinkius as encrypted environment variables, never exposed to the LLM. The server only sends configuration metadata and status metrics back to your LangChain agent.

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