SchemaSure — structured extraction runs on your own machine — the client starts it, so there is no endpoint to ping. 78 installs a week from npm.
Extract schema-valid JSON from text/HTML or document images. Pay with x402 on Base or MPP on Tempo.
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": {
"command": "npx",
"args": [
"-y",
"@noamjose/schemasure"
]
}
}
}
[mcp_servers.schemasure]
command = "npx"
args = ["-y", "@noamjose/schemasure"]
{
"mcpServers": {
"schemasure": {
"command": "npx",
"args": [
"-y",
"@noamjose/schemasure"
]
}
}
}
{
"servers": {
"schemasure": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@noamjose/schemasure"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
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 EVM key for a dedicated spending wallet. Signs x402 Base or MPP Tempo 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), SCHEMASURE_PAYMENT_PROTOCOL (Payment protocol: x402 (USDC on Base) or mpp (USDC.e on Tempo). Signing stays local).
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).
SchemaLock — paid extraction: JSON from docs via your schema, x402/USDC.
Extract structured data from invoices, receipts and other documents with ParserBee.
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.
Extract structured data points from research papers and other documents with an LLM.
Document extraction against a JSON Schema with a calibrated confidence per field; async job status.
Answers built from our own checks of this server.