SchemaSure — structured extraction runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm.
Extract schema-valid JSON from text/HTML or document images. Pay per call via x402 V2.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add schemasure -- npx -y @noamjose/schemasure
{
"mcpServers": {
"schemasure": {
"args": [
"-y",
"@noamjose/schemasure"
],
"command": "npx"
}
}
}
[mcp_servers.schemasure]
command = "npx"
args = ["-y", "@noamjose/schemasure"]
{
"mcpServers": {
"schemasure": {
"args": [
"-y",
"@noamjose/schemasure"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"schemasure": {
"args": [
"-y",
"@noamjose/schemasure"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SCHEMASURE_API_URL (Base URL of SchemaSure. Text has free V1 evaluation without a wallet; image extraction is V2-only and always requires a wallet.), SCHEMASURE_TIMEOUT_MS (Per-call request timeout in milliseconds.), SCHEMASURE_PRIVATE_KEY (Optional 0x-prefixed EVM key. Enables paid x402 V2 text and image calls; signs Base USDC payments locally. Never sent to SchemaSure.), SCHEMASURE_MAX_PRICE_USD (Client-side spend cap in USD per call (paid mode). The client refuses to pay more than this, even if the server advertises a higher price.).
The author declared them in the registry entry; get the values from the project itself.
SchemaLock — paid extraction: JSON from docs via your schema, x402/USDC.
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
Parse and extract structured data from various document formats (PDF, Word, HTML).
Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.
Extract text from documents, manipulate PDFs, and perform OCR on images.
Document extraction against a JSON Schema with a calibrated confidence per field; async job status.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Print & mail PDF/HTML/Markdown/text/DOCX/images to US addresses; pay per call in x402 USDC on Base.
Answers built from our own checks of this server.