JEV Evaluate API

REST API and MCP service documentation generated from server-side API definitions. Responses use the shared code, msg, and data envelope.

API selector

JEV

API overview

Evaluates only the documented preset fields in an authorized, de-identified text excerpt, which is sent to TypeSafe for evaluation. It does not accept custom questions, policy, thresholds, model, identity, or upstream URL. Decisions are advisory: IP triage is not legal clearance, SEO scores do not predict rankings or volume, and evidence checks assess only the supplied excerpt. Requires an active Nexscope subscription. The JEV node does not deduct Nexscope business credits; any selected data API retains its existing billing. Route and evaluate share limits of 20 requests per user per minute, 200 requests globally per minute, and 5,000 requests globally per rolling day; each route or evaluate call counts as one request. Quota admission is sequential: per-user minute, global minute, then global rolling day; an earlier admitted counter remains incremented if a later check rejects the request.

Try this API

Endpoint

/api/skill-api/v1/jev/evaluate

MCP method

nexscope_jev_evaluate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

Missing or invalid API keys return an authentication error. Manage keys from .

POST/api/skill-api/v1/jev/evaluate

Run an API

Maximum serialized request size is 16,000 UTF-8 bytes. Only useCase and its bounded input are accepted; custom questions, policies, thresholds, models, identities, and upstream URLs are rejected.

Slug	`jev-evaluate`
Headers	`Authorization: Bearer nk-...` `Content-Type: application/json`
Request body	API-specific JSON object.
Response body	Platform envelope: code, msg, data, ts, time, cost, traceId. Inspect data.status for asynchronous completion.

Status codes

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

Example request

curl -X POST https://api.nexscope.ai/api/skill-api/v1/jev/evaluate \
  -H "Authorization: Bearer nk-xxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{   "useCase": "response_guardrails",   "input": {     "content": "请勿分享密码；如需帮助，请通过官方网站联系客户支持。"   } }'

All categories/ JEV

POST/api/skill-api/v1/jev/evaluate

Run this API

Send a JSON request to execute this API and receive the documented response payload.

Open tester

Endpoint

Method	`POST`
Path	`/api/skill-api/v1/jev/evaluate`
Auth	`Bearer API key`
Content-Type	`application/json`

Request body

Name	Type	Required	Description
`useCase`	`string`	required	Fixed preset: response_guardrails, ip_risk_triage, seo_relevance, or evidence_check. Allowed: response_guardrails, ip_risk_triage, seo_relevance, evidence_check
`input`	`any`	required	Strict preset input: content; text; query plus at least one SEO dimension; or claim/sourceText with optional quote.

response_guardrails input

Name	Type	Required	Description
`input`	`object`	required	Checks credential_exposure, harmful_instruction, deceptive_claim, instruction_override, and severity. The fixed server policy maps the checks to pass, review, or block.
`input.content`	`string`	required	Authorized response or draft content. Minimum length: 1 Maximum length: 6000

ip_risk_triage input

Name	Type	Required	Description
`input`	`object`	required	Checks trademark, copyright, patent, other IP, and insufficient-context signals plus risk type and severity. The result always requires human review and is not legal clearance.
`input.text`	`string`	required	Authorized product or description text for advisory IP-risk triage. Minimum length: 1 Maximum length: 4000

seo_relevance input

Name	Type	Required	Description
`input`	`object`	required	Requires query and at least one supplied title, metaDescription, or contentExcerpt. Scores relevance only; it does not predict rankings, traffic, search volume, or intent data.
`input.query`	`string`	required	Query value used by this API operation. Minimum length: 1 Maximum length: 500
`input.title`	`string`	optional	Title value used by this API operation. Minimum length: 1 Maximum length: 300
`input.metaDescription`	`string`	optional	Meta description value used by this API operation. Minimum length: 1 Maximum length: 1000
`input.contentExcerpt`	`string`	optional	Content excerpt value used by this API operation. Minimum length: 1 Maximum length: 4000

Any of option 1 — requires title

Name	Type	Required	Description
`input`	`any`	required	Strict preset input: content; text; query plus at least one SEO dimension; or claim/sourceText with optional quote.

Any of option 2 — requires metaDescription

Name	Type	Required	Description
`input`	`any`	required	Strict preset input: content; text; query plus at least one SEO dimension; or claim/sourceText with optional quote.

Any of option 3 — requires contentExcerpt

Name	Type	Required	Description
`input`	`any`	required	Strict preset input: content; text; query plus at least one SEO dimension; or claim/sourceText with optional quote.

evidence_check input

Name	Type	Required	Description
`input`	`object`	required	Assesses the claim only against sourceText. If supplied quote is absent after whitespace normalization, the server returns deterministic quote_not_found without a model call.
`input.claim`	`string`	required	Claim value used by this API operation. Minimum length: 1 Maximum length: 1000
`input.sourceText`	`string`	required	Source text value used by this API operation. Minimum length: 1 Maximum length: 6000
`input.quote`	`string`	optional	Optional quote that must occur in sourceText after whitespace normalization. Minimum length: 1 Maximum length: 1000

Request example

{
  "useCase": "response_guardrails",
  "input": {
    "content": "请勿分享密码；如需帮助，请通过官方网站联系客户支持。"
  }
}

Response body

Nexscope response envelope for a fixed JEV preset. Decisions are advisory and never trigger another API or publishing action.

Name	Type	Required	Description
`code`	`integer`	required	Zero on success; non-zero for validation, access, quota, or availability errors.
`msg`	`string`	required	Response message.
`data`	`object`	required	response_guardrails blocks at risk probability >= 0.85 or severity >= 2 with confidence >= 0.65, reviews at risk probability >= 0.35, severity >= 1, or lower severity confidence, and otherwise passes. ip_risk_triage always returns review and is not legal clearance. seo_relevance passes only when every supplied dimension scores >= 2 with confidence >= 0.65 and does not predict ranking or volume. evidence_check judges only caller-supplied sourceText and may return supported, contradicted, unsupported, uncertain, or deterministic quote_not_found.

Response example

Platform response envelope. code 0 indicates success or acceptance; data contains the business result.

{
  "code": 0,
  "msg": "success",
  "data": {
    "useCase": "response_guardrails",
    "policyVersion": "jev-evaluation-v1",
    "model": "<resolved model>",
    "decision": "pass",
    "reasonCodes": [
      "no_rule_triggered"
    ],
    "checks": {},
    "result": {}
  }
}

Responses

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

Data source, freshness, and limitations

Source, freshness, coverage, rate limits, and estimation notes are not specified in this API definition unless they appear in the request or response field documentation above. Do not assume official marketplace data or real-time freshness when it is not explicitly documented.

Related APIs

JEV Route API

Discover a published Nexscope data API or one of four fixed JEV evaluation presets without executing the selected capability or generating its input.

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/api/skill-api/v2/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json

Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_jev_evaluate",
    "arguments": {
      "useCase": "response_guardrails",
      "input": {
        "content": "请勿分享密码；如需帮助，请通过官方网站联系客户支持。"
      }
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /api/skill-api/v1/mcp

Online test

Execute the current API with your API key and JSON payload.

Pricing pendingAPI usage records

Try it

Send a real request with the same contract shown in the reference.

Endpoint

/api/skill-api/v1/jev/evaluate

MCP method

nexscope_jev_evaluate

API key*

JSON payload*

cURL

curl -X POST \
  https://api.nexscope.ai/api/skill-api/v1/jev/evaluate \
  -H "Authorization: Bearer nk-..." \
  -H "Content-Type: application/json" \
  -d '{ "useCase": "response_guardrails", "input": { "content": "请勿分享密码；如需帮助，请通过官方网站联系客户支持。" } }'

Response

No response yet. Run the request to see the response here.