No zero-width or other invisible characters
Zero-width spaces and joiners, soft hyphens, word joiners and direction marks are invisible; they often come from copy and paste, but they can also split keywords to slip past filters, so remove them from tool metadata.
Check sec-zero-width · Poisoning and hidden text · default severity: attention · rubric 2.1.0
What fails
Zero-width spaces and joiners, soft hyphens, word joiners and direction marks are invisible. Often they come from copy and paste, but they can also split keywords to slip past filters.
The rule
Treat the entire tool schema as a potential injection surface — not just the description field.
Source: OWASP MCP Security Cheat Sheet
How to fix it
Remove the characters. "Copy fixed tool list" strips them.
- Strip U+200B to U+200F, U+2060, U+FEFF and U+00AD from every string.
- Check your editor or generator: copied text from documents is the usual source.
- Add a CI test.
A CI test that fails when the pattern comes back, run against the saved tools/list answer:
TypeScript (node:test)
// tools-list.test.mjs: run `node --test` after saving the answer with
// npx @modelcontextprotocol/inspector --cli <server> --method tools/list > tools.json
import assert from 'node:assert/strict';
import { readFileSync } from 'node:fs';
import { test } from 'node:test';
const answer = JSON.parse(readFileSync('tools.json', 'utf8'));
const tools = answer.tools ?? answer.result?.tools ?? answer;
// Every string and every key in a tool, with its path.
function* strings(value, path) {
if (typeof value === 'string') yield [path, value];
else if (value && typeof value === 'object')
for (const [k, v] of Object.entries(value)) {
yield [`${path}.${k} (key)`, k];
yield* strings(v, `${path}.${k}`);
}
}
const PATTERN = /[\u200B-\u200F\u2060\uFEFF\u00AD]/u;
test('no zero-width or invisible characters', () => {
const hits = [];
for (const tool of tools) for (const [path, text] of strings(tool, tool.name)) if (PATTERN.test(text)) hits.push(path);
assert.deepEqual(hits, [], 'zero-width or invisible characters in tool metadata');
});Python (pytest)
# test_tools_list.py: run `pytest` after saving the answer with
# npx @modelcontextprotocol/inspector --cli <server> --method tools/list > tools.json
import json
import re
with open("tools.json", encoding="utf-8") as f:
answer = json.load(f)
tools = answer.get("tools") or answer.get("result", {}).get("tools") if isinstance(answer, dict) else answer
def strings(value, path):
"""Every string and every key in a tool, with its path."""
if isinstance(value, str):
yield path, value
elif isinstance(value, dict):
for k, v in value.items():
yield f"{path}.{k} (key)", k
yield from strings(v, f"{path}.{k}")
elif isinstance(value, list):
for i, v in enumerate(value):
yield from strings(v, f"{path}.{i}")
PATTERN = re.compile(r"[\u200B-\u200F\u2060\uFEFF\u00AD]")
def test_no_zero_width_or_invisible_characters():
hits = [path for tool in tools for path, text in strings(tool, tool["name"]) if PATTERN.search(text)]
assert hits == [], "zero-width or invisible characters in tool metadata"Questions
Why is this attention and not blocking?
Most zero-width characters in the wild come from copy and paste, not attacks. They are still worth removing: they change tokens and can defeat keyword filters.
Is U+FEFF at the start of a file a problem?
A byte-order mark at the start of a file is harmless; inside a string value it is an invisible character.
Related checks
- No invisible Unicode tag or variation-selector characters
- No control characters in metadata
- No bidirectional override characters
- All checks in Tool poisoning and hidden text
How this check is graded
It counts toward: Poisoning and hidden text, Anthropic connector directory, OpenAI plugin directory. See the rubric.
Last verified against OWASP MCP Security Cheat Sheet on 2026-11-18. The rule above is quoted in the source’s own words. This page as Markdown.
Check your tool list: paste your tools/list, nothing is sent anywhere