io.usefulapi/mindee
REMOTE · MINDEE.USEFULAPI.IO · SCANNED SEP 21
Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security78
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 401, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 596 tokens (~149/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the io.usefulapi/mindee MCP server?
io.usefulapi/mindee is a hosted endpoint at https://mindee.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mindee.usefulapi.io
claude mcp add --transport http io-usefulapi-mindee 'https://mindee.usefulapi.io/mcp'
{
"mcpServers": {
"io-usefulapi-mindee": {
"url": "https://mindee.usefulapi.io/mcp"
}
}
} {
"servers": {
"io-usefulapi-mindee": {
"type": "http",
"url": "https://mindee.usefulapi.io/mcp"
}
}
} [mcp_servers.io-usefulapi-mindee] url = "https://mindee.usefulapi.io/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"io-usefulapi-mindee": {
"type": "remote",
"url": "https://mindee.usefulapi.io/mcp",
"enabled": true
}
}
} openclaw mcp add io-usefulapi-mindee --url 'https://mindee.usefulapi.io/mcp' --transport streamable-http
mcp_servers:
io-usefulapi-mindee:
url: "https://mindee.usefulapi.io/mcp" {
"McpServers": {
"io-usefulapi-mindee": {
"Transport": "http",
"Url": "https://mindee.usefulapi.io/mcp"
}
}
} assistant mcp add io-usefulapi-mindee -t streamable-http -u 'https://mindee.usefulapi.io/mcp'
{
"mcpServers": {
"io-usefulapi-mindee": {
"type": "http",
"url": "https://mindee.usefulapi.io/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 0
- Stability: unverified → 0.03 ▲ functional
- 17 Sept 26 +54
- Transport: unverified → pass ▲ security
- Authorization: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Schema quality: unverified → fail ▼ functional
- Schema quality: unverified → fail ▼ functional
- MCP protocol: unverified → fail ▼ functional
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Schema quality: unverified → excellent ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Destructive annotations: pass functional
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 15 Sept 26 −10
- Transport: pass → unverified ▼ security
- 14 Sept 26 +10
- Transport: unverified → pass ▲ security
- 7 Sept 26 0
- Transport: fail → unverified ▼ security
- 6 Sept 26 −10
- Endpoint reachability: behind authorisation → not serving MCP ▼ security
- Transport: pass → fail ▼ security
- Tool safety: Tool safety not yet verified: we couldn't read the endpoint's tools. security
- Tool coverage: Tool coverage not yet verified: we couldn't read the endpoint's tools. functional
- Capabilities: Capabilities not yet verified: we couldn't read the endpoint's capabilities. functional
- Schema quality: Schema not yet verified: we couldn't read the endpoint's schema. functional
- 5 Sept 26 +10
- Endpoint reachability: not serving MCP → behind authorisation ▼ security
- Transport: unverified → pass ▲ security
- Tool safety: Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools. security
- Tool coverage: Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools. functional
- Schema quality: Schema blocked by authentication: the endpoint requires auth we don't have to read it. functional
- Capabilities: Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Probed https://mindee.usefulapi.io/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=usefulapi.io | CN=WE1,O=Google Trust Services,C=US | 13 Sept 2026 | 12 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 2b7685856a793144132d922b90bf7902 |
| SANs: usefulapi.io, mindee.usefulapi.io, *.mindee.usefulapi.io | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mindee.usefulapi.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 57355 | 8 | Verified |
| usefulapi.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer realm="OAuth", resource_metadata="https://mindee.usefulapi.io/.well-known/oauth-protected-resource/mcp", error="invalid_token", error_description="Missing or invalid access token"
Bearer realm="OAuth", resource_metadata="https://mindee.usefulapi.io/.well-known/oauth-protected-resource/mcp", error="invalid_token", error_description="Missing or invalid access token"Protected resource metadata
| Document | https://mindee.usefulapi.io/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://mindee.usefulapi.io/mcp |
| Authorisation server | https://mindee.usefulapi.io |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mindee.usefulapi.io/mcp | Verified | 200 | |
| http (plaintext) | http://mindee.usefulapi.io/mcp | Inconclusive | 401 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
mindee_extract_document Extract data from a document ~308
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.
| Name | Type | Req | Description |
|---|---|---|---|
| alias | string | – | Your own reference tag echoed back in the job/result. |
| confidence | boolean | – | Return per-field confidence levels (Certain/High/Medium/Low). |
| document_url | string | – | Public URL of the document to process. Use this OR file_base64. |
| file_base64 | string | – | Base64-encoded document bytes. Use this OR document_url; set `filename` too. |
| filename | string | – | Filename for file_base64 uploads, e.g. 'invoice.pdf'. |
| model_id | string | yes | Extraction model id (from mindee_list_models). |
| polygon | boolean | – | Return bounding-box polygons for fields. |
| rag | boolean | – | Enable Retrieval-Augmented Generation for the model, if configured. |
| raw_text | boolean | – | Also return the full OCR raw text of the document. |
| webhook_ids | array | – | Webhook ids to notify on completion (async flows). |
No output schema declared.
No examples provided.
mindee_get_inference Get extraction result ~105
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}.
| Name | Type | Req | Description |
|---|---|---|---|
| inference_id | string | yes | Inference id (from a Processed job's result_url, or from mindee_extract_document). |
| raw | boolean | – | Return the full unshaped API response instead of the compact fields map. Default false. |
No output schema declared.
No examples provided.
mindee_get_job Get job status ~95
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}.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | Job id returned by mindee_extract_document (when it times out) or an enqueue call. |
No output schema declared.
No examples provided.
mindee_list_models List extraction models ~88
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.
| Name | Type | Req | Description |
|---|---|---|---|
| model_type | string | – | Optional model type filter. |
| name | string | – | Optional case-insensitive name filter, e.g. 'invoice'. |
No output schema declared.
No examples provided.
What is the io.usefulapi/mindee MCP server?
io.usefulapi/mindee is an MCP server listed in the public MCP registry as io.usefulapi/mindee. Turn PDFs and images into typed fields, invoices, receipts, IDs and custom models, via Mindee OCR. This page covers its hosted endpoint (https://mindee.usefulapi.io/mcp).
Is the io.usefulapi/mindee MCP server safe to use?
io.usefulapi/mindee scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.usefulapi/mindee MCP server expose?
io.usefulapi/mindee exposes 4 tools: mindee_list_models, mindee_get_job, mindee_get_inference, mindee_extract_document. Their descriptions and schemas cost roughly 596 tokens of context every time the server is loaded.
Does the io.usefulapi/mindee MCP server require authentication?
Yes. io.usefulapi/mindee asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the io.usefulapi/mindee MCP server still maintained?
io.usefulapi/mindee is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.