Paid services on Base matching “unicode”

Guess the character set of a base64-encoded byte buffer: sniffs a byte-order mark, then falls back to ASCII / UTF-8 validation and a UTF-16 NUL-pattern heuristic. Returns a best-effort charset with a confidence label — a low-confidence guess is still a successful 200.

Resolve a Unicode block name (loose matching) to its range, size, count of assigned characters and a small sample. An unknown block is a successful `found:false`. This is a Unicode Character Database block — not a blockchain block.

Web page to markdown (read URL as clean text) for LLM agents: main content only (no nav, cookie banners, ads), with title, description, author, dates, language, headings, internal/external links and JSON-LD types, PLUS a prompt-injection scan of the page (visible text, hidden HTML, comments, invisible Unicode) so your agent knows whether the content tries to give it orders. Fetched from Cloudflare

Prompt-injection screen for text or a web page an agent is about to read: finds instruction overrides (many languages and obfuscated spellings), fake system or role markers, jailbreak personas, data-exfiltration links, requests for keys or seed phrases, tool, shell, or payment hijacks, and hidden content (invisible Unicode smuggling, zero-width and bidi characters, HTML comments, hidden elements,

MCP security: catch a rug pull or tool poisoning between two tools/list results of the same MCP server — the version you approved and the one it serves now. Flags instructions aimed at the model, override and concealment wording, credential and wallet paths, covert actions, hidden Unicode, new URLs and addresses, a dropped readOnlyHint, new command or path parameters and look-alike tool names; ver

Transcribe text to Unicode braille (grade-1 / uncontracted English braille), with capital and number signs. Characters with no grade-1 representation are clean 400s.

Classify text an AI agent is about to read for prompt injection: verdict (safe, suspicious, malicious), score 0-100, findings with matched spans; decodes hidden Unicode tags, HTML comments, CSS-hidden text and base64 before scanning.

MCP Server Scan by Agentropolis: scan a live remote MCP server URL (or pasted tools/list) before your agent connects. Reads initialize + tools/list only, never calls a tool. Flags poisoned or hidden tool instructions (IMPORTANT tags, conceal-from-user, secret or side-channel asks, invisible Unicode, tool shadowing, payment injection). Fingerprints every tool (sha256) and diffs vs your last scan to

Extract text and tables from a Word .docx file ($0.005 USDC via x402). Input: a public https url to a .docx, or docx_base64. https only — http, file, data, localhost, and private IPs are rejected. Caps: 10 MB file, ~15s timeout, max 5 redirects. Tables appear as [table N] placeholders in text. Unicode dashes/minus signs normalized to '-'. Old binary .doc files are not supported. Returns JSON { fil

Safe Read: fetch one public web page and get its clean main text, title, metadata, a sha256 content hash, and prompt-injection warnings with a 0-100 risk score (visible text, hidden elements, HTML comments, alt/meta attributes, invisible Unicode, base64). SSRF-guarded: DNS-checked and pinned public addresses only, 4 redirects max, 2 MB, 8 s, text/html and text/plain only. Errors are not charged.

Statically analyse a Model Context Protocol (MCP) server manifest for security risks. Tool descriptions enter the model context, a prime prompt-injection vector. Deterministic and offline (inline manifest). Flags dangerous capabilities (command/code execution, filesystem, credential and network access), injection patterns, hidden unicode and unconstrained parameters. Returns severity-ranked findin

Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

Compare text using deterministic, case-insensitive bag-of-words token-overlap similarity for lexical duplicate screening. Lowercase each input and tokenize with Python Unicode regex \w+ (letters, digits and underscores). Count repeated tokens. Similarity = sum(min(count_a(token),count_b(token))) / max(words_a,words_b,1), rounded to four decimal places. Returns exactly similarity in [0,1], words_a

Cyrillic transliteration to Latin using a named standard: ISO 9:1995 (one-to-one, with diacritics, covering the full standard: Russian, other Slavic, historic and non-Slavic Cyrillic letters) or BGN/PCGN, which is the Russian system only (Ukrainian, Serbian and other letters are passed through unmapped). Returns the transliteration, the source script, the standard, the mapped fraction and the unma