Turn messy text into strict JSON schemas agents can trust (invoice, receipt, contact, resume).
Scored across 6 tools
There is meaningful overlap between parse_invoice, structure_text, and normalize_data, especially since structure_text and normalize_data both target the same schemas and parse_invoice is a more specific version of structure_text for invoices. extract_table, get_schema, and validate_structure are distinct, but the unstructured-text-to-schema tools have unclear boundaries.
All tool names follow a consistent verb_noun snake_case pattern: extract_table, get_schema, normalize_data, parse_invoice, structure_text, validate_structure. This makes the tool set predictable and easy to navigate.
Six tools is a well-scoped size for a data structuring and validation server. Each tool addresses a meaningful step in the pipeline without excessive redundancy or unnecessary surface area.
The core workflow of extracting, normalizing, and validating structured data is covered, with schema discovery available. The main gap is the lack of a way to create or modify custom schemas, but the curated-schema approach makes this a minor limitation rather than a critical failure.
Extract HTML or markdown tables into JSON rows.
Inputs: html (required).
Discover schema shapes. Pass name for one schema, or omit to list all curated schemas.
Inputs: name.
Normalize data object to a named schema (invoice, receipt, contact, resume).
Inputs: data (required), target_schema (required).
Parse invoice text into vendor, amount, due_date, line_items (with math_check).
Inputs: text (required).
Convert messy text to strict JSON schema. Use for emails, chat logs, unstructured input. Schemas: invoice, receipt, contact, resume.
Inputs: text (required), schema_name.
Validate JSON against a schema. Enforces field presence and types (string/number/date/array).
Inputs: data (required), schema_name (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Convert documents to structured JSON (invoices, receipts, contracts) in 2 seconds
Turn PDFs and photos into typed JSON with your own schema. Missing values come back null.
Add one secure layer between your agents and this server.
