How to Use the Jasper MCP in LangChain

Q: How do I handle Jasper brand voices inside a LangChain sequence?

You call listvoices to retrieve your active brand profiles. Pass the selected voice ID directly to runcommand in your next chain link to enforce your style guide.

Q: Can a LangChain agent dynamically select a Jasper template?

Yes. Your agent calls listtemplates to inspect the available input schemas, then executes the chosen template using runtemplate with the required parameters.

Q: How does LangChain track token consumption for Jasper runs?

Use the getusage tool within your chain to fetch real-time API statistics. You can pipe this data into LangSmith to monitor exact operational costs.

Q: What happens if a Jasper task requires custom context?

The runtask tool accepts a JSON array containing custom context fields. You query gettask first to see the exact context schema your agent needs to build.

Build multi-step LangChain pipelines using this MCP Server to pull brand assets and run content templates directly through Jasper.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jasper MCP to LangChain

Create your Vinkius account to connect Jasper 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 Jasper with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain brand voices into your LangChain runs.

Using this MCP Server, the `list_voices` tool pulls your active brand voices directly into your LangChain sequence. Your chain queries this endpoint first to grab the exact voice ID needed for the next step. This setup passes that ID straight to `run_command` alongside your raw prompt. You get brand-aligned copy back in a single run without manual copy-pasting.

Run template-driven generation inside chains.

The `run_template` tool executes specific Jasper templates using input schemas retrieved from `list_templates`. Your LangChain agent inspects the required JSON structure dynamically before formatting the payload. This means you build chains that feed structured data from database queries directly into Jasper marketing templates. The output matches your expected layout every single run.

Monitor Jasper API usage within LangChain runs.

The `get_usage` tool in this MCP config pulls your actual API consumption metrics using ISO date parameters. Your LangChain supervisor agent calls this endpoint to track token burn rates during high-volume generation loops. If the usage exceeds your set threshold, the chain pauses or switches to a cheaper model. You maintain complete cost control over your automated content pipeline.

Setup guide

Set up Jasper 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 Jasper 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({
    "jasper-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 Jasper 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 Jasper. 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 Jasper 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 Jasper MCP in LangChain

You call `list_voices` to retrieve your active brand profiles. Pass the selected voice ID directly to `run_command` in your next chain link to enforce your style guide.

Yes. Your agent calls `list_templates` to inspect the available input schemas, then executes the chosen template using `run_template` with the required parameters.

Use the `get_usage` tool within your chain to fetch real-time API statistics. You can pipe this data into LangSmith to monitor exact operational costs.

The `run_task` tool accepts a JSON array containing custom context fields. You query `get_task` first to see the exact context schema your agent needs to build.

Your brand voices and audience files remain isolated within the Vinkius V8 sandbox. This MCP environment only transmits the minimum payload required for `get_voice` or `get_document` over encrypted channels, keeping your proprietary style guides secure.

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