text_clean
Clean and normalise messy text before embedding, indexing or prompting: repairs mojibake (UTF-8 read as Windows-1252), strips control and invisible characters (zero-width, bidi overrides used in Trojan Source attacks, soft hyphens, BOM), normalises exotic whitespace, curly quotes, dashes, ligatur...
This record as markdown: /tools/com-it-scorptech-x402/text-clean.md
What text_clean does on ScorpTech x402 API
AI agents call text_clean to retrieve information from ScorpTech x402 API without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to clean |
ascii | boolean | — | Transliterate Latin accents to ASCII (é -> e) |
fullwidth | boolean | — | Full-width ASCII forms to ASCII |
ligatures | boolean | — | Expand fi fl ff ffi ffl ſt st |
lowercase | boolean | — | Lowercase everything |
stripHtml | boolean | — | Remove HTML tags (script/style content dropped) |
removeUrls | boolean | — | Remove http(s) URLs |
dehyphenate | boolean | — | Join words hyphenated across line breaks (infor-\nmation) |
fixMojibake | boolean | — | Repair UTF-8 decoded as Windows-1252 (Café -> Café, ’ -> ’) |
removeEmoji | boolean | — | Remove emoji and pictographs |
unwrapLines | boolean | — | Join hard-wrapped lines inside paragraphs |
removeEmails | boolean | — | Remove email addresses |
Parameters from the server's own tool schema.
Why text_clean is rated Low
Even though text_clean only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (18 properties)
Attacks that exploit this kind of access
The rule that runs text_clean safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ScorpTech x402 API, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For text_clean, this is the rule to start with:
text_clean is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ScorpTech x402 API, apply this rule, and every text_clean call is checked against it from then on.
Questions about text_clean
Clean and normalise messy text before embedding, indexing or prompting: repairs mojibake (UTF-8 read as Windows-1252), strips control and invisible characters (zero-width, bidi overrides used in Trojan Source attacks, soft hyphens, BOM), normalises exotic whitespace, curly quotes, dashes, ligatures and full-width forms, re-joins words hyphenated across line breaks, optionally unwraps hard-wrapped lines, strips HTML, decodes entities, removes emoji / URLs / emails, transliterates to ASCII or lowercases. Reports how many fixes of each kind were made. Offline; 500 KB. Price: $0.001 USDC per successful call (x402, Solana). Same tool over HTTPS: POST https://scorptech.it.com/api/x402/v1/text-clean. It is categorised as a Read tool in the ScorpTech x402 API MCP Server, which means it retrieves data without modifying state.
text_clean accepts 12 parameters: text, ascii, fullwidth, ligatures, lowercase, stripHtml, removeUrls, dehyphenate, fixMojibake, removeEmoji, unwrapLines, removeEmails. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the ScorpTech x402 API MCP server in PolicyLayer and add a rule for text_clean: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ScorpTech x402 API. Nothing to install.
text_clean is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the text_clean rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for text_clean. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
text_clean is provided by the ScorpTech x402 API MCP server (https://scorptech.it.com/api/x402/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ScorpTech x402 API, and thousands of servers like it.
This server
Across the catalogue