SocialDataX 敏感词检测 Sensitive Text Check MCP

check_sensitive_text

Read-only

敏感检测、敏感词检测、违禁词检查与文案合规检查：检查一段社媒文案是否存在潜在平台审核风险。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "check_sensitive_text"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes	需要检查敏感词、违禁词或平台审核风险的原文文本。
`platform`	No	目标平台规则。generic 表示通用敏感检测；xhs、douyin、kuaishou 分别表示按对应平台常见内容审核风险做检测。	generic

Output Schema

Name	Required	Description
`types`	Yes	风险类型列表
`points`	Yes	本次成功调用的积分消耗与账户积分余额。
`summary`	Yes	检测摘要
`platform`	Yes	检测所使用的平台规则
`violation`	Yes	是否存在敏感风险
`highlights`	Yes	命中片段列表
`risk_level`	Yes	整体风险等级
`suggestions`	Yes	修改建议

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 4, 2026

changedOutput schema / properties / points / description

Previous value: -"本次成功调用的积分消耗与调用完成时的账户积分余额。"New value: +"本次成功调用的积分消耗与账户积分余额。"

changedOutput schema / properties / points / properties / balance / description

Previous value: -"本次接口完成时看到的当前积分余额，可为负数。"New value: +"优先返回调用完成时查询到的账户积分余额。查询失败时，回退到本次预扣后的余额快照。余额可为负数。"

Changed2 schema fields changedNov 4, 2026
- changedOutput schema / properties / points / properties / balance / description
```
Previous value: -"本次接口完成时看到的当前积分余额。"New value: +"本次接口完成时看到的当前积分余额，可为负数。"
```
- removedOutput schema / properties / points / properties / balance / minimum
```
Removed value: -0
```
Changed15 schema fields changedNov 3, 2026
- addedOutput schema / properties / highlights / items / properties / end / title
```
Added value: +"End"
```
- addedOutput schema / properties / highlights / items / properties / reason / title
```
Added value: +"Reason"
```
- addedOutput schema / properties / highlights / items / properties / risk_level / title
```
Added value: +"Risk Level"
```
- addedOutput schema / properties / highlights / items / properties / start / title
```
Added value: +"Start"
```
- addedOutput schema / properties / highlights / items / properties / text / title
```
Added value: +"Text"
```
- addedOutput schema / properties / highlights / items / properties / type / title
```
Added value: +"Type"
```
- addedOutput schema / properties / highlights / items / title
```
Added value: +"SensitiveCheckHighlight"
```
- addedOutput schema / properties / highlights / title
```
Added value: +"Highlights"
```
- addedOutput schema / properties / platform / title
```
Added value: +"Platform"
```
- addedOutput schema / properties / risk_level / title
```
Added value: +"Risk Level"
```
- addedOutput schema / properties / suggestions / title
```
Added value: +"Suggestions"
```
- addedOutput schema / properties / summary / title
```
Added value: +"Summary"
```
- addedOutput schema / properties / types / title
```
Added value: +"Types"
```
- addedOutput schema / properties / violation / title
```
Added value: +"Violation"
```
- addedOutput schema / title
```
Added value: +"SensitiveCheckResult"
```
First observedOct 19, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered structurally. The description adds little behavior beyond purpose: it does not say the text is only inspected and never modified, nor mention rate limits or that results map to platform-specific rules. An output schema exists, so omitting return details is acceptable.

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

Conciseness3/5

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

The string '敏感检测、敏感词检测、违禁词检查与文案合规检查' is four near-synonyms for the same operation, consuming front-loaded space without adding information. The single substantive clause afterwards is efficient, but the padded lead-in hurts structure.

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?

With full schema coverage, an output schema, and read-only annotations, the description only needs to convey the tool's purpose, which it does. The remaining gap is minor: it never indicates that platform selection changes the rule set applied, leaving that entirely to the schema.

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

Parameters4/5

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

Schema description coverage is 100%, and the enum for platform is documented per-value, so the schema carries parameter meaning fully. The description contributes nothing parameter-specific (it never mentions platform targeting), which is fine given the coverage but leaves it at the baseline rather than above it.

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?

After a keyword-stuffed opener, the clause '检查一段社媒文案是否存在潜在平台审核风险' names a specific verb (check) and object (social media copy) plus the risk being assessed, which is unambiguous. It is clearly distinct from the only sibling, get_points_balance, so no sibling differentiation is needed.

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

Usage Guidelines3/5

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

The usage scenario is implied by 'check whether a piece of social media copy has potential platform review risk', which tells an agent the general context. There is no explicit when-to-use vs when-not statement, no mention of prerequisites, and no guidance on choosing among platform variants (that only appears in the schema).

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

All SocialDataX 敏感词检测 Sensitive Text Check 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.

Resources

Need Help?