FiatDock

Prompt-injection check for untrusted text ($0.0045)

prompt_injection_check

Read-onlyIdempotent

PAID ($0.0045 USDC via x402). Scan text you are about to read — a fetched web page, an email, a tool description, another agent's message — for the shapes that hijack agents: instruction-override phrasing, a redefined system role or persona, requests to move credentials or keys, hidden directive tags and invisible Unicode. Returns a verdict (malicious / suspicious / no_known_pattern) and every pattern found with its severity. The same ruleset scans every FiatDock marketplace listing. Pattern-based: no_known_pattern is not a guarantee. Up to 8,000 characters per call; nothing is stored. Without payment this returns the 402 challenge; the fiatdock-mcp npm package pays automatically. Any answer the tool cannot produce is >= 400 and is NOT charged.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	No	The text to scan (up to 8,000 characters). Omit the whole body to scan the published example
`payment`	No	Base64 of a single x402 v2 PaymentPayload (EIP-3009 transferWithAuthorization on Base USDC). OMIT it on the first call: the 402 you get back carries `howToPay.payloadTemplate` — the exact envelope to fill in — plus the price and the EIP-712 domain. Send it on the second call to complete the purchase; it is forwarded as the PAYMENT-SIGNATURE header, never as body data. Nothing is charged for the 402 itself, and a call that fails after payment settles nothing.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	Yes	What the verdict does and does not mean
`chars`	Yes	Characters scanned
`method`	Yes	The ruleset applied
`verdict`	Yes	malicious (a high-severity pattern), suspicious (medium only) or no_known_pattern (not a guarantee)
`findings`	Yes	Each pattern found, with its severity and how many times
`checkedAt`	Yes	ISO time of the scan
`defaulted`	No	Present only when the body was empty: which subject the answer is for, and why
`highCount`	Yes	High-severity patterns found
`mediumCount`	Yes	Medium-severity patterns found

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 4, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only cover read/idempotent/openWorld; the description carries the real behavioral load: price ($0.0045 USDC), the 402-challenge-then-pay two-step, the 8,000-character cap, that nothing is stored, that failures >=400 are not charged, and the key caveat that pattern matching means no_known_pattern is not a guarantee.

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?

Dense and front-loaded — purpose, then what it detects, then return shape, then caveat, then pricing/payment logistics. Every sentence earns its place, though the payment logistics run long for a description whose schema already covers them.

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

Completeness5/5

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

An output schema exists, yet the description still names the verdict values and what accompanies them. Combined with the limits, privacy statement, caveat, and payment/error semantics, an agent has everything needed to call it correctly and interpret the result.

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 the baseline is 3: both `text` and `payment` are already documented with equal or greater detail in the schema. The description's added value here is only reinforcement of the 402/PAYMENT-SIGNATURE flow, not new parameter meaning.

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 specific verb (scan) and resource (text about to be read) plus the exact threat class it detects: instruction-override phrasing, redefined persona, credential-move requests, hidden tags, invisible Unicode. It is unmistakable against siblings like web_read or email_check, which fetch/parse rather than scan for injection.

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 concrete when-to-use context ('text you are about to read — a fetched web page, an email, a tool description, another agent's message') and explains the paid-call flow. It stops short of naming an alternative or an explicit when-not-to-use, so it is clear context without exclusions.

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

All FiatDock tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.