How to Use the Observe.AI MCP in Windsurf

Use Windsurf to pull contact center data directly into your workspace. Stop hunting for transcripts and QA scores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Observe.AI MCP to Windsurf

Create your Vinkius account to connect Observe.AI 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 Observe.AI with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain agent coaching with Windsurf

Cascade doesn't just read data; it maps coaching sessions to specific interaction moments. You define the goal, and the agent uses `list_coaching_sessions` alongside `list_interaction_moments` to build a performance timeline. Stop switching tabs. When you need to see how an agent handled a specific call, Cascade pulls the transcript via `get_interaction_transcript` and correlates it with the QA evaluation results.

Analyze interaction quality in Windsurf

Get the full picture of your contact center performance by querying `list_interactions` directly. Cascade identifies trends across thousands of calls without you manually filtering spreadsheets. Every score matters. By using `list_qa_evaluations` and `get_evaluation_details`, you get the granular breakdown of why a call was marked as success or failure.

Manage your workspace with Windsurf

Keep your team data current without leaving your IDE. Cascade uses `list_workspace_users` to verify agent permissions and roles, ensuring you only pull data you have access to. Need to update your rubric? Use `list_evaluation_forms` to see what your current grading criteria look like before making changes to your coaching strategy.

Setup guide

Set up Observe.AI 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 Observe.AI 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 Observe.AI payment history." If connected, Cascade will call the Observe.AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "observeai-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 Observe.AI. 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 Observe.AI 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 Observe.AI MCP in Windsurf

Add the server to your settings and Cascade handles the rest. Once connected, you can ask the agent to fetch transcripts or QA scores using natural language.

Yes. Cascade chains multiple tools to find a trend, grab the relevant interaction, and summarize the coaching outcome in one go.

Only if you explicitly allow it. You manage the server configuration in your local settings, keeping the connection under your control.

The connection is ephemeral. Your data stays between your local environment and the API, with no persistent storage in your IDE.

This server touches interaction metadata, full text transcripts, QA evaluation scores, and coaching session logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.