Mindee MCP by usefulapi

io.usefulapiPublished by usefulapi.ioOfficial publisherv1.35.3Updated Nov 5, 2026

Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.

The publisher's own server: Ably MCP by usefulapi

VerifiedStreamable HTTPWeb executableFiles & StorageData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Hosted Mindee OCR server that lets an assistant extract typed fields from PDFs and images, such as invoices, receipts and IDs.

What you can do
  • List the document-extraction models available on the connected Mindee account
  • Submit a PDF or image by public URL or base64 and get structured extracted fields
  • Check the status of an enqueued job and fetch the finished inference result
  • Report monthly usage, request a missing feature, and upgrade or cancel the paid plan
When to use it
Useful when you want an assistant to pull structured data out of invoices, receipts, IDs or custom Mindee models without building your own OCR pipeline, and you already have or are willing to get a Mindee account.
Requirements
Remote streamable HTTP endpoint; no local install. Sign-in is via OAuth, and on first connect you paste your Mindee API key, which is validated and stored per user. The README says to add only the URL and no Authorization header. A free tier of 50 tool calls per month applies.
Before you install
Documents are sent to a third-party hosted service and on to Mindee for extraction, so avoid sensitive files unless that is acceptable. The server also exposes subscription tools that return Stripe Checkout links and can spend money (Pro $9/month or $90/year, Pro+ $39/month or $390/year); confirm before upgrading or cancelling. Extraction submits data to Mindee, and the README notes no refund for the current paid period on cancellation.

Installation

In SourceWeft

  1. Open Mindee 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%2Fmindee/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": {
    "mindee-by-usefulapi": {
      "type": "http",
      "url": "https://mindee.usefulapi.io/mcp"
    }
  }
}

README

Mindee MCP by usefulapi

Extract structured data from any document with Mindee, from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your Mindee API key.

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

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://mindee.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http mindee https://mindee.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": {    "mindee": {      "url": "https://mindee.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 Mindee credentials.

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

On first connect you'll paste your Mindee API key. It's validated, stored per-user, and scoped to you.

Tools

ToolTypeWhat it does
mindee_list_modelsreadList extraction models
mindee_get_jobreadGet job status
mindee_get_inferencereadGet extraction result
mindee_extract_documentwriteExtract data from a document
mindee_usage_statusmetaUsage status (free-tier meter)
mindee_request_featuremetaRequest a missing feature
mindee_upgrademetaUpgrade to Pro or Pro+
mindee_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$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 mindee_upgrade (it returns a Stripe Checkout link). Cancel any time with mindee_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running mindee_upgrade before then undoes the cancel. Or write to [email protected].

License

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

Source: servers/mindee/README.md at commit 4046075

Tools

4

mindee_list_models

List extraction models

List the document-extraction models available to your Mindee account (id, name, type). Use a model's `id` as the model_id for mindee_extract_document. V2 API: GET /v2/search/models.

Parametersnamemodel_type

mindee_get_job

Get job status

Check the processing status of an enqueued document by job id. Status is Waiting | Processing | Processed | Failed. When Processed, the response carries a result_url; pass that inference id to mindee_get_inference. V2 API: GET /v2/jobs/{job_id}.

Parametersjob_idrequired

mindee_get_inference

Get extraction result

Fetch the structured result of a completed inference by id, returned as a compact map of extracted fields (plus raw_text if it was requested). V2 API: GET /v2/inferences/{inference_id}.

Parametersrawinference_idrequired

mindee_extract_document

Extract data from a document

Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, billed per page). V2 API: POST /v2/inferences/enqueue.

Parametersragaliaspolygonfilenamemodel_idrequiredraw_textconfidencefile_base64webhook_idsdocument_url

Version history

20
  1. v1.35.3LatestNov 5, 2026
  2. v1.35.2Nov 5, 2026
  3. v1.35.1Nov 4, 2026
  4. v1.35.0Nov 3, 2026
  5. v1.34.1Nov 3, 2026
  6. v1.33.0Nov 1, 2026
  7. v1.31.0Oct 31, 2026
  8. v1.30.0Oct 31, 2026
  9. v1.29.2Oct 30, 2026
  10. v1.29.0Oct 30, 2026
  11. v1.24.0Oct 26, 2026
  12. v1.21.3Oct 25, 2026
  13. v1.21.0Oct 25, 2026
  14. v1.20.0Oct 24, 2026
  15. v1.17.0Oct 23, 2026
  16. v1.16.4Oct 22, 2026
  17. v1.16.3Oct 21, 2026
  18. v1.11.1Oct 9, 2026
  19. v1.10.0Oct 9, 2026
  20. v1.0.1Sep 16, 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