How to Use the LinkAce MCP in LangChain

Q: Does the LangChain integration support live search in LinkAce?

Yes, the searchbookmarks tool allows the agent to query your live LinkAce instance in real time. This ensures your RAG pipeline always has access to the latest links you have saved.

Give your LangChain agents a direct line to your LinkAce bookmark archive to read, write, and tag links in multi-step chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkAce MCP to LangChain

Create your Vinkius account to connect LinkAce 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 LinkAce with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain LinkAce tools with other LangChain APIs

This MCP Server exposes your self-hosted bookmark library to your LLM chains, starting with the `list_all_bookmarks` tool to fetch existing links. Your agent can pull down your reading list and run those URLs through document loaders or web scrapers. You can feed the extracted text into summarization chains and automatically tag the original bookmark. The agent uses `create_new_tag` to organize the content and `create_new_bookmark` to update your collection based on the output of previous steps.

Trace every bookmark tool call in LangSmith

The `get_bookmark_details` tool retrieves metadata for specific links, which can be monitored in real time using LangSmith. You get full visibility into the exact inputs and outputs of your bookmarking pipeline without guessing why a run failed. When your agent executes `search_bookmarks` to find relevant reference material, LangSmith tracks the latency and token usage. This lets you debug slow API responses and optimize how your chains query your LinkAce instance.

Build autonomous link management loops

The `delete_bookmark` tool allows your ReAct agent to clean up dead links or outdated references on its own. This MCP capability checks the status of your saved URLs and removes the ones that return 404 errors. By combining `list_all_collections` and `create_new_collection`, your agent can automatically group related links into clean categories. You set the rules, and the agent executes the changes across your entire library.

Setup guide

Set up LinkAce 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 LinkAce 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({
    "linkace-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 LinkAce 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 LinkAce. 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 LinkAce 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 LinkAce MCP in LangChain

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient to connect your MCP Server. Call get_tools to pass the tools directly to your agent executor.

Yes, by running sequential tool calls in a structured loop. The agent can search for specific items using `search_bookmarks` and then run `create_new_tag` for each result in the chain.

Yes, the `search_bookmarks` tool allows the agent to query your live LinkAce instance in real time. This ensures your RAG pipeline always has access to the latest links you have saved.

You can mix these MCP tools with any of the 500+ integrations in the LangChain ecosystem. For example, you can fetch bookmarks and save them directly to a vector database in the same execution run.

Your LinkAce bookmark URLs, tags, and API tokens are never sent to third-party indexing services. All traffic runs through the Vinkius zero-trust MCP sandbox, keeping your private web archive isolated.

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