"OCR agent" matching MCP servers:

Enables AI agents to discover and query enterprise knowledge documents and business metrics through standardized MCP tools, supporting retrieval, structured sales/order analysis, anomaly scanning, and data lineage lookups.

Enables autonomous agents and scraping pipelines to deduplicate high-throughput event streams, repair and validate gigabyte-scale JSONL data, retry HTTP/S requests with exponential backoff and header rotation, mimic Chrome/Safari TLS fingerprints, and sync cross-domain cookie sessions. Tool invocations are metered through x402 USDC micropayments on Base L2, returning a payment challenge until a signed transaction unlocks execution.

An MCP server that exposes Estuary Flow pipeline operations as typed tools, enabling agents to inspect pipeline health, publish captures and materializations, edit/restart tasks, and read landed documents via tool calls.

Enables deterministic reconstruction of complex tables from OCR bounding boxes, including multi-column layouts, merged headers, grid hierarchies, formula auditing, and PII redaction through MCP.

Converts PDF, Word, PowerPoint, Excel, and HTML documents into Markdown, handling files up to 8 MB in a single call and routing larger or scanned files through an OCR and table-detection queue that returns Markdown plus a JSON structure file. Results arrive either by polling or a signed webhook.

Audits extracted balance sheets, income statements, and cash flow reports for mathematical consistency and formula balancing, reconstructing complex financial tables and resolving cross-references from document or OCR payloads. Also performs spatial layout parsing and PII redaction, returning structured matrices and validation telemetry over MCP.

Provides deterministic tools for transforming, formatting, and inspecting structured data for AI agents.

Enables AI assistants and editors to profile, clean, and analyze messy CSV/Excel files directly through MCP tools such as profile_dataset, clean_dataset, and list_sheets.

Enables deterministic reconstruction of complex tables from OCR bounding-box payloads, recovering multi-column layouts, merged headers, and grid hierarchies. It also supports formula consistency auditing and sensitive PII redaction for document processing pipelines.

Enables agents to answer analytics questions with provable correctness by resolving metrics through the semantic layer, tracing lineage, traversing knowledge graphs, checking freshness, and searching glossary definitions, while enforcing access controls and logging every call.

Converts DOCX/XLSX to Markdown with native OOXML chart-data extraction (reads numCache/strCache directly, no OCR or rasterization) and zero-loss composite-figure markers. Ships a CLI, an MCP server (stdio + Streamable HTTP), and an optional VLM fallback for figures with no native chart data.

Turns natural language into data pipeline actions using six specialist agents that collaborate through MCP to build, validate, and monitor data infrastructure.

An MCP server that provides data bridging from Spring Boot interfaces and a lightweight Python sandbox for script execution. It enables agents to fetch data as Markdown or Parquet files and perform automated data analysis within a controlled environment.

Provides an instant MongoDB MCP server that can be used from any AI agent without local installation.

A metadata-guided, read-only SQL analysis MCP server for DataHub that helps agents perform safe analytical queries using DataHub schema, lineage, ownership, and tags, with a deterministic planner and strict SQL safety layer against local synthetic SQLite, guaranteeing zero write or mutation operations.

Enables natural language interaction with JSON files, providing tools to load, query, aggregate, transform, and export data directly from AI editors.

Enables AI agents and MCP clients to heuristically parse multi-column document dumps, aligned spacing, and CSV/TSV input, converting them into clean GitHub Flavored Markdown tables and typed JSON. Runs fully offline on the Python standard library with zero external dependencies, returning deterministic results without LLM round-trips.

Enables read-only interaction with a Databricks workspace, exposing catalog metadata and bounded SQL querying while preserving caller identity through OAuth-protected authorization.

Enables AI agents and MCP clients to convert ASCII/OCR text dumps, aligned spacing, and CSV/TSV data into clean GitHub Flavored Markdown tables and typed JSON deterministically.

Enables SQL queries on WeRead (微信读书) book data by syncing it into DuckDB, with an MCP server for agent-based analysis and cross-source joins.