jump to content

Claude.ai Configuration

Connect the MCP server to Claude.ai’s web interface using native OAuth integration, with example queries and ClaudeAPI programmatic access.

Show as Markdown

This guide explains how to connect the MCPServer platform to Claude.ai, Anthropic’s web interface, allowing Claude to interact with your compliance data directly in the browser.

Claude.ai supports native MCP integration through OAuth – no tokens to manage and no local software to install.

  • A Claude.ai account (Plan Pro, Team or Enterprise)
  • A court running the API platform

Choose the end point for your platform environment:

Environment MCP URL
the platform US https://us.probo.com/api/mcp/v1
the platform EU https://eu.probo.com/api/mcp/v1
Custom https://your-probo-instance.com/api/mcp/v1

The ___ZBT_I18N_RUNTIME_BLOCK_171__ segment is required.

  1. Log into claude.ai
  2. Click on the profile icon in the upper right corner
  3. Go to Settings → Integrations
  1. Click “Add integration”
  2. Enter a name (e.g. Probo)
  3. Enter the platformMCPURL:
https://your-probo-instance.com/api/mcp/v1
  1. Click “Connect”

Claude.ai will open a new window that will redirect you to your platform court. “Authorize” to grant Claude.ai access to your compliance data.

Once authorized, you will be redirected back to Claude.ai – integration is active.

Start a new conversation and ask:

"List all organizations I have access to"

Claude should use the listOrganizations tool and turn your organizations.

You: "Show me all high-priority risks in my organization"
Claude: I'll fetch those for you.
[Uses listRisks tool]
Here are the high-priority risks:
1. Data breach from third-party systems
2. Inadequate access controls
...
You: "Add a new third party called 'CloudStore Inc' that provides storage services"
Claude: I'll add that third party now.
[Uses addThirdParty tool]
Successfully added CloudStore Inc as a third party.
You: "Give me a compliance status overview — open nonconformities, overdue obligations, and active audits"
Claude: Let me gather that data.
[Uses listFindings, listObligations, listAudits]
Here's your compliance summary:
- 3 open nonconformities (1 critical)
- 2 overdue obligations
- 1 active audit (SOC 2 Type II)

For custom applications that use ClaudeAPI, you can also connect to the MCPprogramatic platform server:

import anthropic
client = anthropic.Anthropic(api_key="your_claude_api_key")
response = client.beta.messages.create(
model="claude-opus-4-8",
max_tokens=1024,
mcp_servers=[
{
"type": "url",
"url": "https://your-probo-instance.com/api/mcp/v1",
"name": "probo",
"authorization_token": "your_probo_api_token",
}
],
messages=[
{
"role": "user",
"content": "List all high-priority risks in my organization"
}
],
betas=["mcp-client-2025-04-04"],
)
print(response.content)

Need help with Claude.ai integration?

Ultima actualizare: