Skip to main content
Glama

Prompt Sanitizer — prompt-injection scan for untrusted content

Remove hidden content from untrusted text and flag text aimed at the model

input_guard
Read-only

Removes hidden content and flags text aimed at the model, for untrusted input before an agent acts on it: web pages, emails, RAG chunks, tool and MCP responses. Strips invisible Unicode (tag smuggling decoded, zero-width, bidi) and HTML hidden from people; flags role takeover, forged system or tool turns, requests for keys, the prompt or payments, exfiltration links, homoglyphs and base64 payloads, in 17 languages. Rule-based. Verdict clean, caution or hostile, score, findings, cleaned text. Free with a key (500 calls) or 5 calls a day without one; then 0.02 USDC per call via x402, or 1 call from a key. After: preflight before your agent pays anything the content pointed to (the result's next field has the exact call).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "input_guard"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoa public https page to fetch once and check (256 KB)
textNothe content to check (send text or url)
payment_txNoHash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
bundle_tokenNoYour key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
payer_addressNoWallet you pay from (optional; the x402 price is the same for every address).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / bundle_token / description
      Previous value: -"Token from buy_signal_pack or buy_pack_with_card instead of paying per call."New value: +"Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too."
    • changedInput schema / properties / payer_address / description
      Previous value: -"Wallet you pay from: the payment-required error quotes your tier (0 payments base price (new-payer surcharge paused), 1-10 base, >10 -30 %) and, from the third payment, an upgrade with your own spend."New value: +"Wallet you pay from (optional; the x402 price is the same for every address)."
  2. Changed1 schema field changed
    • changedInput schema / properties / bundle_token / description
      Previous value: -"Token from buy_signal_pack, buy_subscription (pro/desk) or buy_enterprise instead of paying per call."New value: +"Token from buy_signal_pack or buy_pack_with_card instead of paying per call."
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds the method (rule-based, 17 languages), the access model (key with 500 free calls, 5 calls/day without a key, then 0.02 USDC per call via x402, or 1 call from a key), and the return shape (verdict clean/caution/hostile, score, findings, cleaned text). That is substantial behavioral context beyond what the structured fields already say.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and applicable input types, then detection coverage, then pricing. It is dense and slightly run-on in the pricing clause (free with a key... or 1 call from a key), but nearly every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter tool with no output schema and payment/auth branches, the description covers the verdict values, the cleaned-text return, the language scope and the billing path. It omits error behavior and input-size limits (256 KB fetch, 100 K text), which live only in the schema, but the essentials for a correct call are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so url, text, payment_tx, bundle_token and payer_address are already documented at the field level. The description's pricing sentence mostly restates the meaning already in the bundle_token and payment_tx descriptions, and it adds no guidance on choosing text vs url or on the fetch size limits beyond what the schema carries.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb pair (removes hidden content, flags text aimed at the model) and enumerates the exact inputs it applies to: web pages, emails, RAG chunks, tool and MCP responses. It also spells out what is stripped (tag smuggling, zero-width, bidi, hidden HTML) and what is flagged (role takeover, forged turns, key/payment requests, exfiltration links, homoglyphs, base64), so an agent can tell exactly what this tool does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear usage context — untrusted input, run before the agent acts on it — plus a follow-up trigger: preflight before the agent pays anything the content pointed to. There is no explicit when-not guidance and the obvious alternative (input_guard_preview) is never named, so the agent must infer which variant to pick.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.