facehunch
Read-only MCP connector for viewing your saved Facehunch photo-search reports
facehunch is an MCP server for mcp data access. It can run locally on your machine or as a hosted remote server.
- Platforms
- API, CLI, Self-hosted
- Runs
- Locally or Remotely
- Version
- 1.2.1
- Listing updated
Similar MCP servers
Install
Run in a terminal
claude mcp add --transport http mcp-server https://mcp.facehunch.com/mcpAdd to Settings → Connectors → Add custom connector
https://mcp.facehunch.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"url": "https://mcp.facehunch.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp-server": {
"type": "http",
"url": "https://mcp.facehunch.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp-server": {
"serverUrl": "https://mcp.facehunch.com/mcp"
}
}
}Add to Grok Bot desktop app → Connect apps → Add a custom connector
https://mcp.facehunch.com/mcpEnter a Name (for example "facehunch"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.
Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp-server": {
"type": "http",
"url": "https://mcp.facehunch.com/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
About facehunch
This connector lets an AI assistant read reports already saved in a Facehunch account. It can list reports with their status and access details, open a single report to see its stored source links, and check the account profile. Access is granted through browser sign-in with OAuth, so no product password is handed to the assistant.
The connector cannot start new face searches, identify anyone, or research personal information. Locked results stay hidden, and an empty report list only means the account has no saved reports. Similarity scores are not treated as proof of identity.
It suits people who already use Facehunch and want an assistant to summarise their saved reports and keep dates and source URLs intact. It runs as a hosted Streamable HTTP server or as a local stdio package on Node.js 22 or newer.
Tools this server provides (3)
Taken from the project documentation; the running server may differ.
- get_profile
- Read the signed-in account context.
- list_reports
- List reports already owned by the account, with status and access metadata.
- get_report
- Retrieve an owned report's metadata and available stored source links while respecting locked results.
What it does
- Saved report listing
- Shows reports already owned by the account along with their status and access metadata.
- Report detail retrieval
- Opens an owned report to return its metadata and the stored source links that remain accessible.
- Locked result handling
- Keeps locked results hidden and returns the product link instead of guessing their contents.
- Browser OAuth sign-in
- Uses browser-based consent with PKCE so no product password is entered into the assistant.
- Remote and local transports
- Available as a hosted Streamable HTTP endpoint or a local stdio bridge installed through npx.
Good for
- Listing saved photo-search reports with dates and statuses inside an AI assistant
- Summarising the available source links in an existing report without interpreting identity
- Checking whether a saved report is accessible before opening it
- Reviewing account connection permissions alongside the assistant workflow
facehunch FAQ
Can the connector start new face searches?
No. It only retrieves reports that already exist in the account and does not initiate new searches.
How does sign-in work?
You complete Facehunch sign-in in your browser and review the requested permissions, profile:read and reports:read, on the consent screen.
What do I need to run the local version?
Node.js 22 or newer and an existing Facehunch account, added to your client's MCP configuration with npx facehunch-mcp.
Why is my report list empty?
An empty list means the account has no saved reports. It does not mean a photograph has no online matches.
How do I add facehunch to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp-server https://mcp.facehunch.com/mcp
What are the best alternatives to facehunch?
The closest alternatives to facehunch are Passport.Me, Pexels MCP Server and img-src-io.
Where this comes from
- Description: written from the project's README and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.