"OCR agent" matching MCP servers:

An MCP server that gives autonomous coding agents deterministic, schema-validated tools for EVM smart contract development — security scanning, gas profiling, compiler diagnostics, and transaction simulation.

MCP server exposing statistical regression testing for LLM agents as a "run" tool: p-value, effect size, and confidence interval on whether agent behavior actually changed.

A filesystem-based MCP server for AI coding agents to coordinate work across git worktrees by claiming files, checking for conflicts, and logging progress without affecting the repository's git history.

Enables AI agents to read and bid on a paid message slot on Solana, with enforced spend limits, dry-run proposals, and an append-only audit log for every write.

MCP server that exposes tools for natural-language querying of the Chinook SQLite database, enabling agents to discover schema and execute read-only SQL queries dynamically.

Enables Claude Desktop and Claude Code users to get AI-powered legal risk classifications for small business decisions, returning structured GREEN/YELLOW/RED verdicts with statute citations and compliant alternatives.

A read-only MCP server that exposes local coding-agent session logs as three tools for introspection of recent work, debugging tool failures, and tracking token usage and estimated cost without parsing log files.

Provides a local MCP interface to query captured, PII-scrubbed prompt telemetry from coding agents and browser chats, enabling time summaries, prompt search, and activity analysis without data leaving the machine.

Give text-only LLM agents eyes by describing images through a vision-language model via MCP or CLI.

MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.

Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.

Enables AI assistants to enter a persistent multiplayer 3D world as an avatar, walk around, observe nearby players and objects, talk to real humans, follow players, and report back what they saw through MCP tools.

MCP server for WeChat Mini Program debugging and automation, enabling agents to perform UI operations, screenshots, and regression testing through natural language commands.

Enables OCR-enabled PDF to Markdown conversion in Claude Code, with per-page inspection and hybrid handling of text, scanned, mixed, and blank pages via a local vision-model endpoint.

Enables any MCP client to execute DeepSeek Harness agents and shell commands through standard MCP tools, bridging multi-agent capabilities with sandboxed execution.

Enables AI agents to draft AP-style press releases from a product URL and publish them to a public newsroom page, or distribute them across a newswire to hundreds of news, TV and radio sites, with status tracking for wire orders. Paid calls are settled per request in USDC on Base via x402 from the user's own wallet, defaulting to quote-only mode with spend caps and confirmation tokens.

Enables Cursor's AI agent to perform supercharged local file search on Windows by connecting to Agent Ransack via MCP, supporting content and filename searches, regex, and deep folder scans.

Provides structured OCR with verified bounding boxes using the space-ocr API. Allows extraction of structured fields from document images and listing of built-in templates.

Registers a set of inert, tempting decoy tools with any MCP-capable client so that any call from a hijacked or prompt-injected agent instantly raises an alert with full attack context and a per-call trace token. Also plants worthless canary tokens in honeypot files that trigger zero-false-positive leak alerts when they surface in agent output, files, or outbound requests.

A local MCP server that saves work-in-progress checkpoints to SQLite, enabling AI agents to resume interrupted sessions without redoing work.