snapshot-site/snapshot-site-mcp

Official MCP server for the Snapshot Site API
Tools
- screenshot
- analyze
- compare
These tools are annotated for MCP clients as:
- read-only
- idempotent
- open-world
They also include richer titles, category metadata, and example intents to improve tool selection in Claude Desktop and Cursor.
Two ways to connect
**Hosted, with OAuth** — point your client at https://mcp.snapshot-site.com/mcp
and sign in. There is no local process to run and no API key in your client
config; the server resolves your account from the OAuth session.
**Local, with an API key** — run the package yourself over stdio and provide
SNAPSHOT_SITE_API_KEY. The server calls the Snapshot Site API directly.
Either way, calls count against the same plan quota as direct API calls. Nothing
is metered differently because it came through MCP.
Credentials
The hosted server needs no credential — you sign in through OAuth and the server
resolves your account from the session. Skip this section unless you run the
server yourself over stdio.
For local stdio mode you need a Snapshot Site API key.
1. Sign up for a Snapshot Site Console account.
2. Create an API key on the API Keys page.
3. Pass the key to the server as the SNAPSHOT_SITE_API_KEY environment variable.
4. Leave SNAPSHOT_SITE_BASE_URL at its default (https://api.prod.ss.snapshot-site.com)
unless you're pointed at a self-hosted or staging instance.
Compatibility
Requires Node.js 20.9 or later. Built against @modelcontextprotocol/sdk v1.28
and tested with Claude Desktop and Cursor over stdio, and with any client that
speaks the streamable HTTP transport against the hosted endpoint.
Usage
Not sure which options to use? Preview a capture and its parameters in the
Screenshot console playground
before wiring them into a tool call.
OAuth discovery flow
What a client does when connecting to the hosted server:
The server then validates the token against the issuer and resolves the account
it belongs to before running the tool.
Verifying the deployment
Manual vs implicit client_id
- The client_id is only needed for the authorization step.
- If your client cannot discover that client_id beforehand, enter it manually in the connector UI.
- It cannot be injected later once the OAuth flow has started.
- The server can publish an experimental implicit mode by exposing a preferred_client_id in /.well-known/oauth-protected-resource.
- Clients that read this metadata may then skip the manual entry. Clients that ignore the field still require a manual client_id.
Environment
Build
Local stdio mode
Claude Desktop configuration
Cursor configuration
Remote HTTP mode
This package also supports a hosted MCP endpoint for clients using mcp-remote.
Start the HTTP server:
or:
Environment variables:
Remote client configuration with direct API key header:
The hosted server is stateless. Each request authenticates with x-snapshotsiteapi-key, which makes the service safe to run on multiple replicas without session affinity.