Data conversion and parsing

Text encoding repair for AI agents

Fixes garbled characters and normalises Unicode.

utilities.unicode_text_normalizer

What it does

Fixes garbled characters and normalises Unicode. It is one of the Data conversion and parsing tools in the Ahura Utilities catalogue: a ready-made MCP tool that an agent calls with a typed input and gets a structured result back, with no library to install and no sandbox to start.

How agents use it

Agents use text encoding repair to clean scraped text before tokenising it. Because it is a plain tool call, it slots into a single agent turn or a step in an Ahura Workflow, and large inputs and outputs are passed by reference using a store:// address from Ahura Store.

Interactive simulation

Run text encoding repair

Press Run to send the call. The dashboard shows what it would use in a partition. Simulated: nothing is actually executed.

ahura mcp · ptn_demo_7f3a

# Clean scraped text before tokenising it.

→ POST /mcp

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "utilities.unicode_text_normalizer",
    "arguments": {
      "text": "Café"
    }
  }
}

Ready. Press Run.

ptn_demo_7f3a

Partition · N. Virginia · created just now

Simulated

Activeus-eastRetention hold

days left

Run time

0.0s

0 calls

Size

2.3MB

0.00 ACU used

Services in this partition

Utilities
0 calls · 0.00 ACU

Spend by service

Ledger

No usage yet.

Good to know

Billed per call, with the price shown in tools/list. See pricing
Runs inside your partition, so inputs and results stay isolated and follow its retention settings.
Safe to chain: pair it with Ahura Workflows for retries and approvals.

More Data conversion and parsing utilities

All utilities