The request asks for a text processor MCP server, and none of the candidates is a dedicated text-processing tool. The closest matches are general MCP toolboxes and servers that include text, search, or document handling: Clear Line MCP offers 40+ tools including scraping and data extraction 2, Rosetta's PDF MCP server parses and extracts text from digital PDFs 10, and xmcp is a framework for building your own TypeScript MCP server with custom text tools 1. Which fits depends on whether you
A question back: Do you want a ready-made text processing server to connect, or a framework to build your own, and which text task (e.g. PDF extraction, scraping, summarizing, transforming)?
- 1
- 2
PDF MCP Server (Rosetta)rosettafolio.comwebsite read, tools not yet checked
A remote MCP server exposing pdf_parse and pdf_extract tools to pull text out of digital (text-layer, non-OCR) PDFs 10.
- 3
xmcpxmcp.devwebsite read, tools not yet checked
A TypeScript framework for building your own MCP server with file-based tools and Zod validation, so you can write the text processing functions yourself 1.
+3 community tools built for it
Sources
- 1xmcp — The TypeScript MCP frameworkxmcp.dev · read 2026-10-29
- 2Clear Line MCP – Remote MCP server for web search, scraping, domain security, dark web and media toolsmcp.clear-line-operations.com · read 2026-10-29
- 10PDF MCP Server — MCP Tools for Cursor & Claude | Rosettarosettafolio.com · read 2026-10-29
For agents: the 10 actions behind this answer
· xmcp website read, tools not yet checked
Build MCP servers in TypeScript with file-based tools, Zod validation, authentication integrations, and HTTP or STDIO transports. Start with xmcp.
· Clear Line MCP website read, tools not yet checked
Clear Line MCP is a remote Model Context Protocol (MCP) server with 40+ tools for AI agents: web search, scraping, crawling, data extraction, domain and DNS lookup, TLS and security-header checks, .onion directory, QR codes, currency conversion and FFmpeg media processing. Free trial, no card. Day,
get_time_series · Trends MCP found in code, not yet checked
Full historical series for one keyword and one source (0-100
· trace-mcp website read, tools not yet checked
72.7% fewer input tokens to review a pull request — median over 60 merged pull requests in open-source repos we don't own. trace-mcp is a code graph MCP server: it indexes your codebase once so AI agents stop re-reading the same files. Open source, local-first, MCP-native.
· Varity MCP Server Reference website read, tools not yet checked
Install the published Varity MCP package, configure a supported editor, and use its machine-readable tool catalog without relying on unreleased source.
urantia-papers-api · urantia.dev verified and signed
Access and search the Urantia Papers via REST API. Use when retrieving paragraphs, searching text, browsing papers, getting audio narration, or building RAG pipelines over the Urantia Papers.
· McpMux website read, tools not yet checked
The largest MCP server registry and marketplace. Browse and install 100+ Model Context Protocol (MCP) servers for Cursor, Claude, VS Code, ChatGPT, Windsurf, JetBrains, and Gemini CLI. Find MCP servers for GitHub, Slack, PostgreSQL, Docker, AWS, Cloudflare, Atlassian, Notion, Stripe, Sentry, and mor
· state-memory-mcp website read, tools not yet checked
Zero-infrastructure, deterministic Model Context Protocol (MCP) server providing AI coding agents with a structured, persistent SQLite state graph for tracking tasks, decisions, and blockers.
· Smithery Brave Brave Search website read, tools not yet checked
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key. Tools: - search_web_p
· Rosetta website read, tools not yet checked
Remote PDF MCP server for Cursor and Claude agent builders — MCP tools pdf_parse, pdf_extract, pdf_split, pdf_ask over Streamable HTTP or local npm. Digital PDFs in pipelines, not chat-with-PDF. Not OCR.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.