- Managed service: Hosted by Fingerprint. No setup or maintenance required.
- Open source: Self-host anywhere for full control over deployment and configuration.
Prerequisites
To use the Fingerprint MCP server, you need an active Fingerprint account and permission to create API keys in your workspace. No additional setup is required before connecting. API keys and workspace access are configured automatically during the OAuth connection flow.Connection Details
Server URL
Authentication
The Fingerprint MCP server uses OAuth. When you connect your AI client, you will be redirected to the Fingerprint dashboard to authorize access and select the workspace to connect to. If you have only one workspace, the selection step is skipped automatically. If your AI client does not support OAuth, you can authenticate by passing your API key directly in the client’s configuration. Go to the Fingerprint dashboard for configuration options.Installation
Claude (Claude.ai / Claude Desktop)
Claude (Claude.ai / Claude Desktop)
Fingerprint is listed in the Anthropic connectors directory, so you do not need to enter the server URL. See the Claude Connector documentation for general setup instructions.Adding Fingerprint as a custom connectorIf the directory listing is not available to you, add the server manually instead.
1
Open Connectors
Go to Settings > Connectors and click Browse.
2
Find Fingerprint
Search for
Fingerprint, then click Connect.3
Authorize
Complete the OAuth authorization in your browser when prompted, then select the workspace to connect.
1
Open Connectors
Go to Settings > Connectors and add a custom connector.
2
Add the server
Set Name to
Fingerprint and URL to https://mcp.fpjs.io/mcp, then click Add.3
Connect
Find Fingerprint in the Not connected list and click Connect.
4
Authorize
Complete the OAuth authorization in your browser when prompted.
Claude Code
Claude Code
See the Claude Code MCP documentation for general setup instructions.
1
Add the server
Run the following command to add the Fingerprint MCP server:
2
Open the MCP menu
Start Claude Code and open the MCP menu:
3
Authorize
Select Fingerprint and complete the OAuth authorization in your browser when prompted.
Cursor
Cursor
See the Cursor MCP documentation for general setup instructions.
1
Open Cursor Settings
Go to Cursor > Settings… > Cursor Settings.
2
Add a custom MCP server
Navigate to Tools & MCP and click Add Custom MCP. Add this configuration to your
mcp.json:3
Connect
Return to Tools & MCP and click Connect to authenticate with Fingerprint in your browser.
VS Code (GitHub Copilot)
VS Code (GitHub Copilot)
See the VS Code MCP documentation for general setup instructions.Quick setup: Open the Command Palette (
Ctrl+Shift+P / ⇧⌘P), run MCP: Add Server, and follow the guided flow for remote servers.Manual setup:1
Open your MCP config
Create or open
.vscode/mcp.json in your project (to share with your team), or open the Command Palette and run MCP: Open User Configuration to configure across all workspaces.2
Configure the server
Add the following to your
mcp.json:3
Connect
Save the file. Click Start above the Fingerprint server entry, then complete the OAuth authorization in your browser.
Other MCP Clients
Other MCP Clients
Any MCP-compatible client can connect to the Fingerprint MCP server.
1
Add the server
Follow your client’s documentation for adding an MCP server.
2
Configure the URL
Set the server URL to
https://mcp.fpjs.io/mcp.3
Authorize
Authenticate with OAuth in your browser when prompted.
Available Tools
Tools are divided into two groups: event tools for querying identification data, and management tools for administering your Fingerprint workspace.- Event tools let you retrieve and search identification events, including Smart Signal data like bot detection, VPN, proxy, incognito mode, and more.
- Management tools let you create, update, and delete workspace environments and API keys, and set up custom subdomains.
Custom subdomain tools
The subdomain tools let your AI assistant set up a custom subdomain without the CLI or dashboard:list_subdomainslists all subdomains in your workspace and their status.get_subdomainreturns one subdomain with its DNS records and status.create_subdomainregisters a new subdomain and returns the DNS records to add.verify_subdomainruns a DNS check on demand instead of waiting for the next background check.connect_subdomainreturns a Domain Connect link so you can approve the DNS records in one step. If your DNS provider doesn’t support Domain Connect, your AI assistant shows you the records to add manually.
get_subdomain, verify_subdomain, and connect_subdomain accept either the subdomain ID or its hostname, such as metrics.yourwebsite.com. To delete a subdomain, use the dashboard, the CLI, or the Management API.
For a full list of tools, see the tool reference in the GitHub repository.
Example Queries and Prompts
Once connected, you can ask your AI assistant questions in plain language. Some examples:- Fetch the last 50 events for visitor ID
Abck1234CUFmcnjLwIs4A9and summarize their activity. - Find all events linked to order ID
3936532456and tell me if anything looks suspicious. - Show me recent events where a bot was detected, filtered to the last 6 hours.
- List all environments in my workspace and create a new one called “staging”.
- Set up
metrics.yourwebsite.comas a custom subdomain, then check whether it’s active.
onboarding prompt, a guided walkthrough for integrating Fingerprint into a new project that covers JavaScript agent installation and verification steps. Trigger it by asking your AI assistant to walk you through Fingerprint setup.
Security Considerations
Prompt injection
Fields likelinkedId and tags are customer-controlled values attached to identification events. If a malicious actor controls what gets stored in these fields, they could attempt to embed instructions that manipulate your AI assistant. Most AI clients show you each tool call before it executes, so keep manual approval enabled and review them before confirming.
Sensitive operations
Management tools can create, edit, and delete API keys and environments, and create custom subdomains. Avoid connecting the server in shared or untrusted AI environments. Before approving any destructive changes, particularly in production, take time to carefully review what the agent is proposing.Troubleshooting
Authentication failures
- Ensure you completed the OAuth flow and selected the correct Fingerprint workspace.
- Try disconnecting and reconnecting the MCP server in your client settings.
- If workspace authorization fails, your account may have reached the maximum number of allowed API keys (typically 5). Remove an unused key from the Fingerprint Dashboard and try again.
Tools not appearing
- Restart your MCP client after adding the server configuration.
- In Claude, start a new conversation. Claude caches the tool list for the lifetime of a conversation, so a conversation started before a tool was added will not show that tool. Disconnecting and reconnecting the connector does not refresh a conversation that is already open.
- If you added Fingerprint as a custom connector and no tools appear at all, check the connector name. Names containing dots, apostrophes, or accented characters can prevent Claude from finding the server’s tools. Rename it to
Fingerprint, or connect from the connectors directory instead.
Rate limit errors
- Reduce the number of concurrent or rapid sequential tool calls.
- Use specific filters (
visitor_id,linked_id, time ranges) to reduce the number of API requests needed to answer a question.