How to Use the Endorsal Testimonials MCP in LangChain

Q: How do I connect the Endorsal Testimonials MCP Server to a LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient to connect to the server URL. Once connected, call client.gettools() to pass the testimonial tools directly into your createagent function — and that's it — your agent is ready to moderate.

Q: Can LangChain agents automatically approve reviews using Endorsal Testimonials?

Yes, your agent can poll for new submissions using listpendingtestimonials and then execute approvependingtestimonial based on custom criteria. You can monitor the execution latency and tool inputs of these approvals using LangSmith tracing.

Q: Can I manage multiple brand websites in a single LangChain session?

Yes. Use listaccountproperties to retrieve all configured websites, then pass the specific property ID to tools like listdisplaywidgets to filter your search.

Run LangChain agents that instantly pull reviews, audit social proof, and approve testimonials.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Endorsal Testimonials MCP to LangChain

Create your Vinkius account to connect Endorsal Testimonials 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 Endorsal Testimonials with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate review approval chains in LangChain

`list_pending_testimonials` feeds raw, unapproved customer reviews directly into your LangChain ReAct agent's decision-making loop. The agent evaluates the sentiment of each incoming review, filters out obvious spam, and determines if the submission matches your brand guidelines. Once the agent verifies the review is clean, it triggers `approve_pending_testimonial` to publish it immediately. This automated chain cuts down manual moderation time from hours to seconds while maintaining a strict quality filter.

Audit widget performance across properties

`quick_social_proof_audit` gives your LangChain chain a high-level summary of all active widgets and recent testimonial volume. Your agent uses this metric-driven snapshot to detect sudden drops in customer submissions or widget engagement. By chaining this audit with `list_account_properties`, the agent flags which specific websites are missing active social proof display widgets. This lets you run scheduled diagnostic chains that keep your conversion assets healthy across all domains.

Inject contextual reviews into agent outputs

`search_testimonials_by_keyword` lets your LangChain pipeline search for specific customer quotes using names or target keywords. This tool pulls exact matches to dynamically insert real user feedback into outbound sales drafts or support responses. The chain then feeds the results to `get_testimonial_details` to extract the exact star rating and customer avatar URL. LangSmith traces the entire retrieval process, ensuring your MCP agent never pulls irrelevant or low-rated reviews.

Setup guide

Set up Endorsal Testimonials 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 Endorsal Testimonials 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({
    "endorsal-testimonials-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 Endorsal Testimonials 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 Endorsal Testimonials. 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 Endorsal Testimonials 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 Endorsal Testimonials MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` to connect to the server URL. Once connected, call `client.get_tools()` to pass the testimonial tools directly into your `create_agent` function — and that's it — your agent is ready to moderate.

Yes, your agent can poll for new submissions using `list_pending_testimonials` and then execute `approve_pending_testimonial` based on custom criteria. You can monitor the execution latency and tool inputs of these approvals using LangSmith tracing.

Your LangChain chain should implement backoff strategies when executing multiple tool calls like `list_all_testimonials`. You can also configure the agent to run a `quick_social_proof_audit` first to assess current volume before pulling detailed records.

Yes. Use `list_account_properties` to retrieve all configured websites, then pass the specific property ID to tools like `list_display_widgets` to filter your search.

This server transmits customer names, email addresses, and testimonial text directly through a secure V8 sandbox using ephemeral environments. No review data is stored on our servers, ensuring your customers' details remain private.

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