The Sequentum MCP server lives at:Documentation Index
Fetch the complete documentation index at: https://docs.sequentum.com/llms.txt
Use this file to discover all available pages before exploring further.
In your data pipeline
The primary path. Your Python service or other automation calls Claude (via the Anthropic API) with the Sequentum MCP server attached — the model picks the right agent, runs it, and your pipeline gets structured records without writing a separate REST integration.authorization_token is an OAuth 2.0 access token issued by Sequentum’s authorization server. Mint one out-of-band with any standard OAuth client library, or proxy through your own user-OAuth flow if your pipeline runs per-user.
From an automation platform
n8n, Zapier, AWS Step Functions, and other platforms with MCP support: drophttps://mcp.sequentum.com/mcp into their MCP integration screen and complete the OAuth flow. The server appears as a tool source for any LLM step in the workflow.
From Claude Desktop
For analysts driving Sequentum interactively — “pull today’s pricing data,” “show me yesterday’s failed runs.”- Open Settings → Connectors.
- Click Add custom connector.
- Paste
https://mcp.sequentum.com/mcpas the URL. - Sign in when prompted.
Free Claude plans support one custom connector at a time. Team and Enterprise plans support multiple but require admin enablement first.
Self-hosted
For air-gapped pipelines or on-prem data lakes that can’t reachmcp.sequentum.com. Open source (MIT) at github.com/Sequentum/sequentum-mcp. Requires Node 18+. Generate a Sequentum API key from Control Center → Users → Manage API keys — keys start with sk-.
Dev tools
Useful for prototyping pipeline logic from your editor. Not the production path.- Cursor v1.0+ — one-click install or paste
https://mcp.sequentum.com/mcpinto Cursor’s MCP settings. - Claude Code —
claude mcp add --transport http sequentum https://mcp.sequentum.com/mcp.
Troubleshooting
OAuth callback fails or times out
OAuth callback fails or times out
Usually a popup-blocker. Re-trigger the connect flow with popups enabled, or copy the callback URL from the client logs and complete the exchange manually.
429 Too Many Requests
429 Too Many Requests
Sequentum’s standard API rate limits apply (100 requests / 60-second window per identity). Long-running tool loops in the calling LLM can trip this — your client should respect
Retry-After. See Errors.Tools don't appear in the calling LLM
Tools don't appear in the calling LLM
Check the platform supports MCP HTTP transport. The OAuth grant may also have lapsed — reconnect from the platform’s MCP settings.