How to Use the Deep Talk MCP in CrewAI

Q: How do I limit which Deep Talk tools a CrewAI agent can use?

You can use toolfilter within MCPServerHTTP to restrict tool access. This prevents a writer agent from accessing administrative tools like getaccountdetails using the MCP protocol.

Deploy specialized agent crews to analyze sentiment and extract topics from your support logs using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deep Talk MCP to CrewAI

Create your Vinkius account to connect Deep Talk to CrewAI 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 Deep Talk with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign specialized tasks using CrewAI

`list_extracted_topics` identifies the primary themes and importance scores inside your support datasets. In a CrewAI setup, a researcher agent calls this tool to find recurring customer complaints. A separate analyst agent then takes those topics and runs `search_topics_by_keyword` to find specific examples. The agents share context dynamically to build a unified report.

Monitor sentiment via MCP Server tools

`get_sentiment_analytics` extracts the distribution of sentiment scores across your entire conversation dataset. Your moderator agent reads these scores to flag highly frustrated customer accounts. The agent then assigns follow-up tasks to human agents. Because CrewAI supports hierarchical execution, the moderator coordinates these steps without human intervention.

Manage processing pipelines

`list_analysis_datasets` lists all conversation datasets uploaded for analysis along with their processing status. Your pipeline coordinator agent uses this tool to schedule new runs. The coordinator monitors active jobs via `list_processing_tasks`. It prevents new datasets from queuing until current NLP runs complete.

Setup guide

Set up Deep Talk MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Deep Talk tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Deep Talk Analyst",
    goal="Access and analyze Deep Talk data via MCP.",
    backstory="Expert analyst with direct Deep Talk access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Deep Talk transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Deep Talk Analyst",
        goal="Access and analyze Deep Talk data via MCP.",
        backstory="Expert analyst with direct Deep Talk access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Deep Talk transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Deep Talk. 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 Deep Talk 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 Deep Talk MCP in CrewAI

Pass your Vinkius endpoint URL directly into the agent's mcps parameter. For advanced setups, use MCPServerHTTP to filter which tools each agent can access.

Yes, agents share memory. Once the researcher agent calls list_conversation_clusters, the analyst agent can read those clusters to investigate specific customer issues.

You can use tool_filter within MCPServerHTTP to restrict tool access. This prevents a writer agent from accessing administrative tools like get_account_details using the MCP protocol.

The server supports stdio, SSE, and Streamable HTTP transports. You can configure the transport type directly inside your CrewAI tool setup.

No, the raw customer conversation data is processed within Vinkius's secure sandbox. Only the structured outputs from tools like get_sentiment_analytics are passed to your CrewAI agents.

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