Claude.ai Configuration
Use the Probo MCP Server with Claude.ai web interface
This guide explains how to connect the Probo MCP Server to Claude.ai, Anthropic’s web-based interface, enabling Claude to interact with your compliance data directly in the browser.
Claude.ai supports native MCP integration via OAuth — no tokens to manage and no local software to install.
Prerequisites
Section titled “Prerequisites”- A Claude.ai account (Pro, Team, or Enterprise plan)
- A running Probo instance with API access
Endpoint
Section titled “Endpoint”Choose the endpoint for your Probo environment:
| Environment | MCP URL |
|---|---|
| Probo US | https://us.probo.com/api/mcp/v1 |
| Probo EU | https://eu.probo.com/api/mcp/v1 |
| Custom | https://your-probo-instance.com/api/mcp/v1 |
The /v1 segment is required.
Connect Probo to Claude.ai
Section titled “Connect Probo to Claude.ai”1. Open Integrations Settings
Section titled “1. Open Integrations Settings”- Log into claude.ai
- Click your profile icon in the top-right corner
- Go to Settings → Integrations
2. Add the Probo MCP Server
Section titled “2. Add the Probo MCP Server”- Click “Add integration”
- Enter a name (e.g.
Probo) - Enter your Probo MCP URL:
https://your-probo-instance.com/api/mcp/v1- Click “Connect”
3. Authorize via OAuth
Section titled “3. Authorize via OAuth”Claude.ai will open a new window redirecting you to your Probo instance. Log in if prompted, then click “Authorize” to grant Claude.ai access to your compliance data.
Once authorized, you’ll be redirected back to Claude.ai — the integration is active.
Verify Connection
Section titled “Verify Connection”Start a new conversation and ask:
"List all organizations I have access to"Claude should use the listOrganizations tool and return your organizations. If it does, the connection is working.
Example Interactions
Section titled “Example Interactions”Risk Management
Section titled “Risk Management”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 systems2. Inadequate access controls...Third-Party Management
Section titled “Third-Party Management”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.Compliance Status
Section titled “Compliance Status”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)Programmatic Access
Section titled “Programmatic Access”For custom applications that use the Claude API, you can also connect to the Probo MCP server programmatically:
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)import Anthropic from "@anthropic-ai/sdk";
const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY,});
const response = await anthropic.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: process.env.PROBO_API_TOKEN, }, ], messages: [ { role: "user", content: "Show me all open nonconformities", }, ], betas: ["mcp-client-2025-04-04"],});
console.log(response.content);Support
Section titled “Support”Need help with Claude.ai integration?
- GitHub Issues - Report issues or request features
- Discord Community - Get help from the community
- Anthropic Support - Claude.ai specific questions