CrossingKey MCP

Purchase Secret Pattern Scan

secret.scan

Idempotent

PAID $0.01 USDC on Base via x402. Detects selected credential patterns and returns classifications and positions, not matched values. Heuristic, not comprehensive. Calling this MCP tool returns a payment challenge and does not autonomously spend funds.

Input Schema

Name	Required	Description	Default
`text`	Yes	Input text, maximum 65536 UTF-8 bytes.

Output Schema

Name	Required	Description	Default
`asset`	No
`error`	No
`input`	No
`price`	No
`pay_to`	No
`status`	No
`accepts`	No
`network`	No
`resource`	No
`capability`	No
`extensions`	No
`purchaseId`	No
`instruction`	No
`x402Version`	No
`entitlementId`	No
`execution_url`	No
`execution_mode`	No
`payment_required`	No
`payment_required_header`	No
`settlement_expectations`	No
`confirmation_expectations`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 15, 2026

changedOutput schema / additionalProperties
```
Previous value: -falseNew value: +true
```

addedOutput schema / properties / accepts

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "properties": {},
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / entitlementId
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / error
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / extensions

Added value: +{
+  "additionalProperties": true,
+  "properties": {},
+  "type": "object"
+}

addedOutput schema / properties / purchaseId
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / resource

Added value: +{
+  "additionalProperties": true,
+  "properties": {},
+  "type": "object"
+}

addedOutput schema / properties / status
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / x402Version

Added value: +{
+  "const": 2,
+  "type": "number"
+}

removedOutput schema / required

Removed value: -[
-  "payment_required",
-  "execution_mode",
-  "capability",
-  "input",
-  "price",
-  "asset",
-  "network",
-  "pay_to",
-  "execution_url",
-  "payment_required_header",
-  "settlement_expectations",
-  "confirmation_expectations",
-  "instruction"
-]

AddedOct 10, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Goes well beyond the annotations: it names the exact cost and network ($0.01 USDC on Base via x402), discloses a privacy-relevant output trait (positions/classifications, never matched values), flags the heuristic limitation, and explains the payment-challenge flow including that no funds are spent autonomously. That is exactly the kind of context annotations cannot carry. No contradiction with readOnlyHint=false, since payment/non-autonomous spend is consistent with a non-read-only call.

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

Conciseness5/5

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

Four short sentences, zero filler, and the cost/payment gate is front-loaded so an agent sees the commercial requirement first. Every sentence carries distinct information.

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, so return structure needn't be described, and the description still usefully characterises the output (no matched values). For a single-parameter, paid, open-world scan tool, the agent has everything needed to decide and invoke.

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 coverage is 100% for the single 'text' parameter, so the schema already documents its type and 65536-byte limit. The description adds nothing about the parameter, which is the expected baseline when the schema does the work.

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

Purpose4/5

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

States a specific verb and resource ('Detects selected credential patterns') and pins down the return nature ('classifications and positions, not matched values'). It doesn't name the obvious sibling pii.scan or otherwise distinguish itself from it, so an agent must infer the boundary from the word 'credential' alone.

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

Usage Guidelines2/5

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

The description gives a scope caveat ('Heuristic, not comprehensive') but no when-to-use instruction and no comparison against pii.scan or the other scan/audit siblings. The agent is left to guess which scan tool fits a given input.

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

All CrossingKey MCP 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.