How to Use the Deep Talk MCP in Windsurf

Q: How do I install the Deep Talk MCP Server in Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server details under the mcpServers key. You can also use the Cascade Settings UI to add it visually. Click Refresh in the MCP panel to load the tools.

Q: Why does Windsurf need my Deep Talk account details?

Cascade uses getaccountdetails to verify your remaining processing credits before starting a massive NLP job. It prevents the agent from failing halfway through an analysis.

Q: What happens if a Deep Talk dataset is still processing?

The agent runs getdatasetmetadata to check if the NLP clustering has finished. If the dataset is still crunching, Cascade will read the status and tell you to wait.

Connect the Deep Talk MCP Server to Windsurf and let Cascade analyze customer support conversations autonomously.

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 Windsurf

Create your Vinkius account to connect Deep Talk to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Zendesk ingestion tasks in Windsurf

The `list_connected_sources` tool fetches your Zendesk and Intercom sync status directly into your editor. The MCP connection lets Cascade read the data volume ingested from each platform without you leaving the workspace. You ask for a sync check, and the agent handles the API calls. Following up on slow imports happens automatically. If a sync looks stuck, Cascade chains `list_processing_tasks` to check completion percentages on active ingestion jobs. It figures out why your latest support tickets have not hit the NLP pipeline yet.

Map conversation sentiment

Your agent uses `get_sentiment_analytics` to pull the exact distribution of positive, neutral, and negative scores across any dataset. You tell Windsurf to find out why churn spiked last week. Cascade pulls the dataset, runs the tool, and shows you the raw sentiment breakdown. Digging deeper requires no extra prompts. Cascade grabs the relevant models via `list_available_nlp_models` and applies them to the raw data. It chains these steps to give you a complete picture of customer frustration before you even write a line of reporting code.

Extract Deep Talk topics via MCP Server

Running `list_conversation_clusters` groups semantically similar support tickets into distinct buckets. Cascade looks at these clusters, grabs the representative keywords, and drops a summary file into your project. You get hard data on what users are complaining about. Searching for specific bugs takes one step. Cascade fires `search_topics_by_keyword` to find out how many times a login error popped up in the latest dataset. Then it uses `list_extracted_topics` to rank those themes by importance score.

Setup guide

Set up Deep Talk MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Deep Talk MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Deep Talk payment history." If connected, Cascade will call the Deep Talk tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "deep-talk-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server details under the `mcpServers` key. You can also use the Cascade Settings UI to add it visually. Click Refresh in the MCP panel to load the tools.

Yes. Cascade handles multi-step operations autonomously. If you ask for a sentiment report, it will find the dataset, check the processing status, and pull the metrics without asking for permission at each step.

Cascade uses `get_account_details` to verify your remaining processing credits before starting a massive NLP job. It prevents the agent from failing halfway through an analysis.

The agent runs `get_dataset_metadata` to check if the NLP clustering has finished. If the dataset is still crunching, Cascade will read the status and tell you to wait.

This server processes raw support tickets and chat transcripts from your connected platforms. Vinkius isolates the connection in a V8 sandbox, meaning your Zendesk or Intercom data never leaks to other workspaces.

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