How to Use the AniList GraphQL MCP in LangChain

Q: Can a LangChain agent search for anime and update my list in a single run?

Yes, the agent runs a loop where it first calls searchmedia to find the correct ID. Once it gets the result, it passes that ID directly to savemedialistentry to add it to your watchlist in the same chain execution.

Q: Can I limit which tools my agent can access?

Yes, you filter the tools array returned by client.gettools() before passing them to your agent constructor. For example, you can expose only getairingschedule if you want a read-only bot.

Let your LangChain agents build active anime watchlists, search studios, and track airing schedules in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AniList GraphQL MCP to LangChain

Create your Vinkius account to connect AniList GraphQL 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 AniList GraphQL with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain AniList GraphQL queries together with LangChain

The `get_media` tool starts a chain that lets your LangChain agent grab anime details and feed them directly into the next step. If your agent finds a show, it can immediately trigger `get_studio` to map out the production history without you writing any glue code. You can trace this entire sequence in LangSmith to see exactly how your LangChain agent decides to update your AniList watchlist. When a tool like `save_media_list_entry` runs, you see the exact token usage and payload details in your logging dashboard.

Automate watchlist updates using ReAct agents

The `get_viewer` tool lets your LangChain agent check your current AniList profile and see what you are currently watching. It compares this against the seasonal releases it finds via `get_airing_schedule` to spot new episodes you missed. If it finds a match, it invokes `save_media_list_entry` to bump your LangChain-managed anime watchlist progress based on actual TV schedules. You get a fully autonomous manager that keeps your anime profile fresh.

Build deep character and staff research pipelines

The `get_character` and `get_staff` tools expose raw data so your LangChain agent can crawl complex anime production connections. Your chain can look up an actor, find all their roles, and then cross-reference them with your favorite shows. It uses `toggle_favourite` to mark voice actors you love in AniList based on the LangChain agent's analysis. The agent handles the multi-step reasoning, deciding when to search and when to update your profile.

Setup guide

Set up AniList GraphQL 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 AniList GraphQL 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({
    "anilist-graphql-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 AniList GraphQL 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 AniList. 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 AniList GraphQL 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 AniList GraphQL MCP in LangChain

You pass your token to the Vinkius platform, which handles the secure connection. From your Python code, you just initialize `MultiServerMCPClient` pointing to the Vinkius endpoint, and the agent gets instant access to tools like `update_user` without managing raw headers.

Yes, the agent runs a loop where it first calls `search_media` to find the correct ID. Once it gets the result, it passes that ID directly to `save_media_list_entry` to add it to your watchlist in the same chain execution.

LangSmith logs every single tool call, showing you the exact query variables sent to `get_character` or `get_media`. If the API returns an error, you see the raw response payload in your trace timeline, making debugging simple.

Yes, you filter the tools array returned by `client.get_tools()` before passing them to your agent constructor. For example, you can expose only `get_airing_schedule` if you want a read-only bot.

Your personal watchlists and profile settings are never stored on Vinkius. The platform uses sandboxed V8 isolates to run the server, passing your API requests directly to AniList and destroying the execution context immediately after.

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