TextClean MCP
Server Details
Free deterministic PDF, Markdown, citation, invisible-character, and formatting cleanup for agents.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
With only one tool there is no possibility of misselection, and clean_text's scope is explicitly bounded (deterministic cleanup; explicitly not OCR, grammar correction, or file handling). No overlapping sibling tools exist to create confusion.
The single tool follows a clear snake_case verb_noun convention (clean_text) that matches its function exactly. There is no mixed convention or vague verb to penalize.
One tool is thin for a server surface, even a narrow one; batch cleaning, preset discovery, and quota/status inspection are handled only implicitly through parameters or errors. The tool is well-parameterized, so the count is borderline rather than clearly wrong.
For a stateless deterministic cleaning service, clean_text covers the core operation with presets, destination rendering, and structured output. Minor gaps exist — no batch/multi-input call, no way to query remaining quota, and large inputs must be chunked under the 20000-code-unit cap.
Available Tools
1 toolclean_textText cleanup and destination formattingAInspect
Clean supplied text deterministically without rewriting its meaning. Use for copied PDF text, Markdown/HTML artifacts, citations, spacing, or destination formatting; not OCR, file uploads, grammar correction, or AI-authorship detection. Preserves supported document structure unless a selected cleanup removes it. Returns cleanedText, destination-rendered text, optional html, a changes list, and usage counters as structured JSON and matching JSON text. No API key required. 20 calls per UTC day per network address; shared networks share this allowance. Service-wide load protection can return HTTP 429; honor Retry-After. Maximum 20000 UTF-16 code units per call. Accepted processing attempts consume quota, including repeats. Input and results are processed remotely in memory, not stored or logged; only quota metadata is retained. Validation and quota failures return errors. Example: {"text":"A split para-\ngraph.","preset":"pdf","destination":"email"}.
Inputs: text (required), preset, destination, stripMarkdown, +2 more. Returns: html, text, usage, changes, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Any URL to clean markdown/JSON; PDF, XLSX, CSV, DOCX to text and tables. Free tier for agents.
Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
Web page to clean Markdown for agents. Pay per call ($0.003 USDC on Base) via x402.
Web pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceConvert PDFs, Word documents, Excel/CSV files, and YouTube videos into clean, structured Markdown for AI agents, LLMs, and knowledge tools.1-
- AlicenseAqualityBmaintenanceConvert PDF, DOCX, HTML, and URLs into clean, LLM-ready markdown with tables preserved and boilerplate stripped, through three MCP tools (URL, local file, or raw bytes). Hosted API with no local dependencies; 50 free conversions with a self-serve key, then $0.002 per call.343 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides deterministic, verifiable text/code/measurement utilities for AI agents, enabling tasks like unit conversion, citation formatting, diffing, proofreading, readability scoring, and syntax checking with re-executable proof.14 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceProvides AI agents with comprehensive document parsing capabilities including PDF text extraction, OCR, HTML-to-markdown conversion, table extraction, and summarization, optimized for agent workflows.75 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.