How to Use the Liaison MCP in Claude Code

Q: How do I connect the Liaison MCP Server to Claude Code?

Run claude mcp add --transport http liaison-mcp -- in your terminal. This command updates your /.claude.json configuration file, allowing your CLI client to immediately execute enrollment queries.

Q: How does Claude Code handle large Liaison data exports?

The terminal client uses listexports to identify available files and getexport to retrieve the data. You can pipe this output directly to local command-line tools like jq or redirect it to a local file for processing.

Q: How do I verify my connection to the admissions database?

Ask your CLI client to run the checkliaisonstatus tool. It returns a direct connection status, confirming whether your terminal can reach the admissions API before you run complex batch queries.

Query applicant tracking and manage enrollment data directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liaison MCP to Claude Code

Create your Vinkius account to connect Liaison to Claude Code 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 Liaison with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run terminal-based applicant audits with this MCP Server.

The `list_applications` tool queries your enrollment pipeline directly inside Claude Code so you can check applicant files without opening a browser. You pass specific parameters to filter down to active files, then use `get_application` to pull down the exact document status or academic history you need. This terminal setup lets you pipe raw JSON payloads of student records into local grep or jq commands. SREs can write shell scripts that run these tools to monitor admissions queues and alert staff when a critical application stalls.

Script batch exports directly from Claude Code.

The `list_batches` tool retrieves pending applicant batches, while `get_batch` downloads the specific applicant records you need to sync with your internal database. You instruct Claude Code to check these batch IDs, allowing this MCP Server to run differential updates overnight. By scheduling these commands through a local cron job, your terminal client automatically checks `list_exports` and `get_export` to grab fresh CSVs. No manual browser downloads are needed to keep your university's local database updated.

Query academic programs and custom fields in the shell.

The `list_programs` tool exposes current academic offerings, and `list_custom_fields` shows the exact metadata fields configured for your university's application portal. You ask Claude Code to verify these fields directly from your command line to ensure your database migrations match Liaison's schema. Combining these tools with `list_designations` allows you to map specific majors to incoming applicant records without leaving your terminal. Developers can quickly test API connectivity using `check_liaison_status` before deploying automated enrollment scripts.

Setup guide

Set up Liaison MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see liaison-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Liaison transactions." It will automatically discover and invoke the available Liaison tools.

Terminal

claude mcp add --transport http liaison-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Liaison 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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "liaison-mcp": {
      "type": "url",
      "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 Liaison. 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 Liaison 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 Liaison MCP in Claude Code

Run `claude mcp add --transport http liaison-mcp -- ` in your terminal. This command updates your `~/.claude.json` configuration file, allowing your CLI client to immediately execute enrollment queries.

Yes, you can write shell scripts that call Claude Code to run `list_applications` and output the results. This lets you monitor incoming university applications through cron jobs or terminal-based pipelines.

The terminal client uses `list_exports` to identify available files and `get_export` to retrieve the data. You can pipe this output directly to local command-line tools like jq or redirect it to a local file for processing.

Ask your CLI client to run the `check_liaison_status` tool. It returns a direct connection status, confirming whether your terminal can reach the admissions API before you run complex batch queries.

All applicant tracking records, academic program details, and custom fields remain inside a secure, ephemeral V8 isolate sandbox. Your credentials and student PII are never stored on external servers, keeping your university data compliant with local privacy policies.

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