"PDF" matching MCP servers:

Local Markdown-to-PDF MCP server with four tools to list themes, render a document, validate an existing PDF, and create a document from a template. Requires Python, Pango/GLib, and fonts; its 0–100 report is heuristic, not print or accessibility certification.

Validates PDF page-tree integrity by checking that page kids resolve to page objects, content streams are properly referenced, no orphan pages exist, and counts match, while also flagging blank pages via missing text operations.

Enables AI assistants to inspect generated .docx and .pdf files before delivery, extracting structural, typographic, spacing, and language facts so formatting errors can be caught automatically.

Accessibility-first LaTeX publishing engine with an embedded MCP server. Tools to list registered documents, render template-driven documents, and audit built PDFs for PDF/UA-2 / WTPDF / PDF/A-4f conformance with veraPDF. MIT-licensed.

Generates quality control plans and inspection reports from technical-drawing PDFs: tolerances, fits, threads, GD&T and surface finishes are extracted automatically by Imnoo's drawing analysis, numbered as balloons with acceptance limits and measuring instruments, and exported as a ballooned drawing PDF, an inspection package and an Excel measurement report.

An MCP server that automatically discovers API endpoints from any codebase, generates and runs tests, and produces per-role QA audit reports in PDF and XLSX.

WCAG-Compliance/wcagc-mcp lets an assistant run real axe-core accessibility scans through the user's own wcagc account, rather than guessing accessibility from markup it can see. Tools cover a single URL or PDF, a full-site crawl, saved multi-step journeys, and violation trends.

Lets assistants send the same test prompts to as many as four text models across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry, then automatically grade each answer with a judge model, rule checks and a policy gate. Returns scored leaderboards with letter grades, per-response strengths and weaknesses, latency, throughput and estimated cost, plus downloadable PDF and CSV reports.

Website testing MCP server built for AI agents: 63 Playwright tools with hard assertions, auto form-fill, persistent authenticated sessions, network mocking, and accessibility/SEO/GEO + Lighthouse audits.

Connects an LLM to specialized MCP servers via stdio, enabling authenticated GitHub repository, issue, file, and code operations alongside TF-IDF retrieval over employee PDF records and QA test-case generation and result validation. It exposes tools, a read-only resource, and reusable prompt templates so a client can discover and orchestrate multiple capabilities in one workflow.

Enables archival of any public URL as interactive snapshot (rrweb, PDF, PNG) and autonomous web QA for apps (register, scan, generate and run end-to-end flows).

Enables AI agents to build, flash, and monitor ESP-IDF projects on real hardware, including serial sessions and pytest-embedded hardware tests.

Review AI-generated HTML slides or reports in the browser, anchor comments to specific passages, and have the agent fix them via MCP, with tools for inspection, commenting, layout checking, and export to PDF/PPTX.

Exposes a live Chrome browser to any MCP client through a single local endpoint, enabling real-tab control, DOM interaction, cookies and session use, network/console capture, PDF export, and CDP-powered debugging.

Enables deliverable conformance and evidence-chain checks by turning requirements into executable specs, validating numbers against a provenance ledger, and auditing PDF/OOXML metadata and archive manifests.

This MCP server provides a tool to generate manual test cases in Markdown or CSV format from documentation files and custom rules. It supports text and PDF inputs and can leverage LLM sampling to automate the creation of detailed test scenarios.

Writes German business letters and emails (DIN 5008) from Markdown: typesets letters to PDF/A via Typst and measures every finished PDF against target dimensions, so a misplaced fold mark fails instead of being printed. Runs locally over stdio; no network access while rendering.

Enables AI agents to validate deliverables (JSON, ZIP, PDF, DOCX) against signed contracts, generating verifiable receipts with Ed25519 signatures.

Enables AI assistants to control browser automation through natural language prompts using Playwright, supporting visual element interaction, PDF generation, screenshots, and testing assertions.

A collection of MCP servers providing utilities including user greeting, message decoding, text file reading with PDF summary generation, and NASA-quality code auditing using a trained AI model to predict software defects and measure code complexity.