"OCR agent" matching MCP servers:

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

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 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 tools to issue, verify, and export cryptographically signed receipts for AI agent actions, enabling tamper-proof audit trails for compliance with regulations like the EU AI Act.

Calibrd Agent scores a job against your CV from inside your assistant: fit, seniority gaps, ATS/recruiter CV read, and predicted interview questions. Reports are free (3/day); cover letter and a time-boxed pass unlock when you ask, voice mock stays in Calibrd.com/workspace.

Scans any website to generate an Agent Readiness Report based on the ASO framework, evaluating agent discoverability, trust, interoperability, and commerce readiness.

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 MCP-compatible agents to perform web searches via the agent-web-search engine, returning ranked results with sources.

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.

An MCP server for Perplexity's Agent API, enabling multi-step web research with citations through tools to start, collect, and cancel research runs.

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.

Deploys AI agents on-chain into the Metaplex Agent Registry on Solana, minting Core assets with EIP-8004 identity. Supports self-custodial signing via server keypair or external wallets, with devnet support for free rehearsal.

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.

An MCP-based conversational HR agent that handles time tracking queries, policy lookups, adjustment approvals with human confirmation, and BigQuery analytics via natural language.

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.

Exposes Semgrep as deterministic, rule-matching analysis tools over MCP so a code-review agent can scan only the lines changed in a diff, scan whole files on demand, and check analyzer availability, version, ruleset, and limits. Results are returned as compact per-finding lines with source snippets suitable as comment anchors, along with counts of suppressed out-of-diff matches.

Deterministically evaluates whether a proposed agent spend action matches a supplied policy, returning ELIGIBLE, DENY, or STEP_UP with stable reason codes. Provides local policy evidence only, not payment authorization.

Extracts text and images from PDFs and image files using the Mistral OCR API, with a security sandbox for file writes.

Verifies agent actions against mandates via a single tool, returning allow, deny, or requires_approval receipts without executing the actions.