Skip to main content

​
Use these docs with AI tools

Most integrations against Upwell are now written with an AI assistant in the loop. This site ships machine-readable surfaces so that assistant reads the same verified truth you do — including the per-endpoint retry and delete semantics baked into the API reference and the generated vocabulary.
These surfaces cover the public docs. Pages that require authentication are not included in llms.txt, llms-full.txt, or the Markdown exports — those are built from the public pages only.

​
Point your assistant at the docs

llms.txt

A machine-readable index of every public page — the sitemap your AI tool reads first. Also served at /.well-known/llms.txt.

llms-full.txt

The full content of the public docs in one file, for tools that ingest everything up front instead of following links.
Every page is also available as plain Markdown — append .md to its URL (for example, docs.upwell.com/authentication.md), or press Cmd+C (Ctrl+C on Windows) on any page to copy it as Markdown for pasting into a conversation.

​
The contextual menu

The menu at the top of every page bundles these handoffs into one click: copy the page as Markdown, view it raw, open it as context in Claude or ChatGPT, connect the docs MCP server to Cursor or VS Code, or copy the MCP server URL. On API reference pages it can also download the OpenAPI spec directly.

​
Connect your Upwell workspace data

The read-only Upwell connector lets an AI assistant look up your organization’s invoices, receivables aging, remittances, carrier invoices, shipments, notes, and attached freight documents. It connects to:
You need an active Upwell Admin, Manager, Team Member, or system administrator account and a workspace with MCP access enabled. Cash-application-only accounts cannot connect; ask your Upwell administrator about account access. Contact Upwell support if your workspace does not have MCP access. For Claude Free, Pro, or Max, open Customize > Connectors and choose + Add > Add custom connector. Free accounts are limited to one custom connector. For Team or Enterprise, an organization owner must first add Upwell under Organization settings > Connectors > Add > Custom > Web; Enterprise users with the required custom role can also add it. See Claude’s setup guide for the required organization roles. When adding the connector, enter the server URL above and choose Sign in now and Use Claude’s published identity when prompted. Team and Enterprise members then find Upwell under Customize > Connectors and choose Connect. Sign in to Upwell, check the workspace and account on the consent screen, and choose Allow Access. For ChatGPT, use the published Upwell app when available to your account. Custom setup on ChatGPT web depends on your plan and workspace permissions: Pro supports limited read/fetch connections; Business requires an owner or administrator; Enterprise/Edu also allows authorized members to create connections. Only owners and administrators can publish workspace connections. Follow OpenAI’s current setup guide for plan eligibility and the current connection flow using the server URL above. Every request follows your existing Upwell workspace and role permissions. The connector cannot change records, approve invoices, send messages, or move money. You can revoke a connection in Account > Connected apps in Upwell or disconnect it in your AI assistant. Try asking:
  • “How much do our customers owe us, and how much is overdue?”
  • “What is blocking carrier invoice 55120?” (use an invoice number from your workspace)
  • “Who signed the POD for load 784512, and when?” (use one of your shipment numbers)
Record links open Upwell after sign-in. Document download links expire, and document text and page images are available only after the document has been processed. Check important amounts and conclusions against the source records before acting.

​
Connect the documentation search server

The docs host a search MCP server at:
Once connected, your AI tool can search and retrieve doc content live while you work — ask it “is POST /api/rest/carriers retry-safe?” and it answers from the same idempotency contract documented here, instead of guessing.
Agents and tools can also discover the server without configuration via the standard discovery document at /.well-known/mcp.

​
skill.md

For agents that consume skill files, an automatically generated capability summary of the Upwell platform is available at docs.upwell.com/skill.md. It stays in sync with the docs and requires no maintenance; agents connected to the MCP server can also discover it as an MCP resource.

​
What to rely on

AI answers are only as good as their source. Two properties of these docs are worth knowing when you delegate to an assistant:
  • Generated, not typed — enum values on the vocabulary page and the endpoint schemas in the reference come from Upwell’s live OpenAPI pipeline, so an assistant reading them can’t inherit hand-typo’d values.
  • Behavioral contracts live on the endpoint pages — where an endpoint has a non-obvious contract (retry safety, delete semantics, in-200 business errors), it’s stamped onto that generated endpoint page, so landing there from search surfaces it.
If an assistant’s claim about the API contradicts these docs, trust the docs — and if the docs turn out wrong, tell us; that’s a bug we fix at the source.