JEV

JEV Route API

Discover a published Nexscope data API or one of seven fixed JEV evaluation presets without executing the match. The routing intent is sent to TypeSafe for evaluation. Requires an active Nexscope subscription. Each route or evaluate call deducts 1 Nexscope credit; 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.

MCP tool name

nexscope_route_api

MCP endpoint

https://api.nexscope.ai/mcp

JSON-RPC method

tools/call

Authentication

Use OAuth 2.1 Authorization Code with PKCE and the mcp:tools scope. API keys remain supported as a compatibility option.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

If authentication fails, ask the user to open API Access and copy a valid key.

Call this MCP tool

Initialize an MCP 2025-11-25 Streamable HTTP session at https://api.nexscope.ai/mcp, then use tools/call.

{
  "jsonrpc": "2.0",
  "id": "jev-route-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_route_api",
    "arguments": {
      "categorySlug": "amazon-marketplace-intelligence",
      "intent": "Fetch Amazon product reviews by ASIN so I can analyze customer pain points"
    }
  }
}

MCP 2025-11-25 · Streamable HTTP

Progress is delivered on the original POST SSE response. GET SSE carries notifications; reconnecting must query existing asynchronous work rather than submit again.

Arguments

Name	Type	Required	Description
`intent`	`string`	required	One routing intent. It is used only for discovery and is never converted into API or evaluation input. Example: Fetch Amazon product reviews by ASIN so I can analyze customer pain points
`categorySlug`	`string`	optional	Optional current public catalog category, or jev-evaluation to limit discovery to the fixed presets. Example: amazon-marketplace-intelligence

Response fields

Treat structuredContent as the programmatic API response payload.

Name	Type	Required	Description
`code`	`integer`	required	Zero on success; non-zero for validation, access, quota, or availability errors.
`data`	`object`	required	For matched, call the returned endpoint separately after collecting its required fields. For ambiguous, ask the user to clarify and route again. For no_match, do not invent or execute a capability.
`data.candidates`	`array`	required	Up to three clarification candidates for an ambiguous result.
`data.candidates[]`	`object`	required	Up to three clarification candidates for an ambiguous result.
`data.catalogVersion`	`string`	required	Catalog timestamp used for this routing decision.
`data.confidence`	`number \| null`	required	Confidence value used by this API operation. Minimum: 0 Maximum: 1
`data.match`	`any`	required	Null for ambiguous and no_match responses.
`data.models`	`array`	required	Resolved model versions used by the routing stages.
`data.models[]`	`string`	required	Resolved model versions used by the routing stages.
`data.policyVersion`	`string`	required	Server-owned routing policy version.
`data.reason`	`string`	required	Reason value used by this API operation. Allowed: matched, clarification_required, no_supported_api
`data.status`	`string`	required	Status value used by this API operation. Allowed: matched, ambiguous, no_match
`msg`	`string`	required	Response message.

Published data API match

Name	Type	Required	Description
`data.match`	`object`	required	Null for ambiguous and no_match responses.
`data.match.docsPath`	`string`	required	Docs path value used by this API operation.
`data.match.endpoint`	`string`	required	Endpoint value used by this API operation.
`data.match.kind`	`string`	required	Kind value used by this API operation. Constant: skill_api
`data.match.mcpToolName`	`string`	required	Mcp tool name value used by this API operation.
`data.match.method`	`string`	required	Method value used by this API operation. Constant: POST
`data.match.name`	`string`	required	Name value used by this API operation.
`data.match.schemaEndpoint`	`string`	required	Schema endpoint value used by this API operation.
`data.match.slug`	`string`	required	Slug value used by this API operation.

Fixed JEV use-case match

Name	Type	Required	Description
`data.match`	`object`	required	Null for ambiguous and no_match responses.
`data.match.docsPath`	`string`	required	Docs path value used by this API operation.
`data.match.endpoint`	`string`	required	Endpoint value used by this API operation.
`data.match.kind`	`string`	required	Kind value used by this API operation. Constant: jev_use_case
`data.match.mcpToolName`	`string`	required	Mcp tool name value used by this API operation.
`data.match.method`	`string`	required	Method value used by this API operation. Constant: POST
`data.match.name`	`string`	required	Name value used by this API operation.
`data.match.schemaEndpoint`	`string`	required	Schema endpoint value used by this API operation.
`data.match.schemaPointer`	`string`	required	Schema pointer value used by this API operation.
`data.match.useCase`	`string`	required	Use case value used by this API operation.

One of option 3

Name	Type	Required	Description
`data.match`	`null`	required	Null for ambiguous and no_match responses.

Examples

Example arguments

{
  "categorySlug": "amazon-marketplace-intelligence",
  "intent": "Fetch Amazon product reviews by ASIN so I can analyze customer pain points"
}

Example structuredContent

{
  "code": 0,
  "data": {
    "candidates": [],
    "catalogVersion": "<catalog version>",
    "confidence": 0.91,
    "match": {
      "docsPath": "/api-docs/amazon-reviews-list?view=api",
      "endpoint": "/api/skill-api/v1/skills/amazon-reviews-list/run",
      "kind": "skill_api",
      "mcpToolName": "nexscope_amazon_reviews_list",
      "method": "POST",
      "name": "Amazon Reviews List",
      "schemaEndpoint": "/api/skill-api/v1/skills/amazon-reviews-list",
      "slug": "amazon-reviews-list"
    },
    "models": [
      "<resolved model>"
    ],
    "policyVersion": "jev-routing-v2",
    "reason": "matched",
    "status": "matched"
  },
  "msg": "success"
}