Typless MCP by usefulapi

io.usefulapiPublished by usefulapi.ioOfficial publisherv1.0.0Updated Nov 7, 2026

Extract fields from business documents and read extraction results in Typless.

The publisher's own server: Ably MCP by usefulapi

VerifiedStreamable HTTPWeb executableFiles & StorageData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Hosted Typless server that lets an assistant extract fields and line items from business documents and read back extraction results.

What you can do
  • Extract fields from a document synchronously, or start an async extraction and get an extraction id
  • List finished extractions that have not been polled yet and fetch one extraction's status and result
  • Check monthly usage, request a missing feature, upgrade to Pro or Pro+ and cancel the Pro subscription
When to use it
Useful when you want an assistant to pull structured fields such as supplier, dates and line items out of invoices or other business documents in a Typless account, or to check on and collect finished extraction results.
Requirements
Remote MCP endpoint, no local install. Sign-in is via OAuth; on first connect you supply your Typless API key (the Token value under Settings, API Keys), which the server validates and stores per user. No keys go in client config. Documents are sent as base64 or as a public https URL, and the document type must already exist in the Typless account.
Before you install
Extraction tools are write operations that send your documents to Typless; confirm before running them. The server stores your Typless API key per user. Usage is metered: free plan is 50 tool calls a month, and upgrade tools return Stripe Checkout payment links, so a subscription can cost money; cancellation runs to the end of the paid period with no refund for the current period. Extraction results are deleted 48 hours after processing finishes.

Installation

In SourceWeft

  1. Open Typless MCP by usefulapi in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.usefulapi%2Ftypless/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "typless-by-usefulapi": {
      "type": "http",
      "url": "https://typless.usefulapi.io/mcp"
    }
  }
}

README

Typless MCP by usefulapi

Use your Typless account from Claude, Cursor, or any MCP client. It extracts fields and line items from business documents and reads back the results. Hosted, no local install: connect with your own credentials.

Live endpoint: https://typless.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://typless.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http typless https://typless.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
json
{  "mcpServers": {    "typless": {      "url": "https://typless.usefulapi.io/mcp"    }  }}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Typless credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/typless/

On first connect you provide your Typless API key (the Token value under Settings → API Keys). The server validates it and stores it per user. No keys go in config files.

Tools

ToolTypeWhat it does
typless_list_awaiting_pollreadList finished extractions
typless_get_extractionreadGet an extraction result
typless_extract_datawriteExtract data from a document
typless_extract_data_asyncwriteStart an extraction
typless_usage_statusmetaUsage status (free-tier meter)
typless_request_featuremetaRequest a missing feature
typless_upgrademetaUpgrade to Pro or Pro+
typless_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro (per user)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with typless_upgrade (it returns a Stripe Checkout link). Cancel any time with typless_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running typless_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

Source: servers/typless/README.md at commit 2450437

Tools

4

typless_list_awaiting_poll

List finished extractions

List extraction ids that finished in the last 2 days and were not polled yet. Use typless_get_extraction with each id to read the result. Typless API: GET /api/v1/awaiting-poll.

Parameterscustomer

typless_get_extraction

Get an extraction result

Get the status and result of one extraction by extraction_id. status is IN_PROGRESS, SUCCESS, ERROR or EXPIRED; result is empty until the status is SUCCESS. Calling it also removes the id from typless_list_awaiting_poll. The result is deleted 48 hours after processing finishes. Typless API: GET /api/v2/get-extraction-data.

Parametersocr_dataextraction_idrequired

typless_extract_data

Extract data from a document

Extract fields from one document and wait for the result in the same call. Send the file as base64. Accepts PDF, JPG, PNG, TIFF and BMP up to 10 MB; use typless_extract_data_async for larger files. The document type must exist in the customer's Typless account. Typless API: POST /api/v1/extract-data.

Parameterscustomerfile_namerequiredfile_base64requireddocument_type_namerequired

typless_extract_data_async

Start an extraction

Start an extraction and return an extraction_id at once (HTTP 202). Send the file as base64 (file_base64) or as a public https URL (file_url), not both. file_url files can be up to 35 MiB and must download within 60 seconds. Read the result later with typless_get_extraction. Typless API: POST /api/v1/extract-data-async.

Parameterscustomerfile_urlfile_namerequiredfile_base64file_passworddocument_type_namerequired

Version history

1
  1. v1.0.0LatestNov 7, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Usefulapi integrations