Cloud API

Base URL

https://api.runcontext.dev

All requests require an API key in the Authorization header:

Authorization: Bearer <your-api-key>

Authentication

API keys are generated in the dashboard under Settings → API Keys. Each key is scoped to an organization and inherits the user’s role permissions.

Role	Read	Publish	Manage
Viewer	Yes	No	No
Editor	Yes	Yes	No
Admin	Yes	Yes	Yes

Endpoints

Publish a Semantic Plane

POST /api/v1/orgs/{org}/publish
Content-Type: application/json

Body: The compiled manifest JSON (output of context build).

Response:

{
  "version": 3,
  "products": 4,
  "published_at": "2026-03-08T12:00:00Z"
}

This is what context publish --org my-org calls under the hood.

Get the Latest Semantic Plane

GET /api/v1/orgs/{org}/plane

Returns the latest published manifest for the organization.

List Data Products

GET /api/v1/orgs/{org}/products

Returns a summary of all published data products with names, descriptions, and tier scores.

Get a Data Product

GET /api/v1/orgs/{org}/products/{name}

Returns full detail for a single data product: models, fields, governance, rules, lineage.

Search

GET /api/v1/orgs/{org}/search?q={query}

Full-text search across all models, fields, descriptions, and glossary terms.

MCP Endpoint

The hosted MCP server is available at:

https://api.runcontext.dev/mcp/{org}

This is a standard MCP endpoint that supports Streamable HTTP transport. Configure it in your AI tool’s MCP settings:

{
  "mcpServers": {
    "contextkit-cloud": {
      "url": "https://api.runcontext.dev/mcp/my-org",
      "headers": {
        "Authorization": "Bearer <api-key>"
      }
    }
  }
}

The hosted MCP server exposes the same 8 tools as the local server:

context_search — full-text search across your semantic plane
context_explain — detailed explanation of any model, field, or term
context_validate — check the plane for errors and warnings
context_tier — compute tier scores for any model
context_golden_queries — retrieve pre-validated SQL queries
context_guardrails — get required filters and constraints
context_list_products — list all data products
context_get_product — get full detail for a product

Rate Limits

Plan	Requests/minute	Requests/day
Team	60	10,000
Enterprise	300	100,000

Rate limit headers are included in every response:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 58
X-RateLimit-Reset: 1709913600

Errors

Standard HTTP status codes:

Code	Meaning
401	Invalid or missing API key
403	Insufficient permissions for this action
404	Organization or resource not found
429	Rate limit exceeded
500	Server error

Error responses include a JSON body:

{
  "error": "not_found",
  "message": "Organization 'my-org' not found"
}

CLI Integration

The CLI has built-in cloud commands:

# Publish to cloud
context publish --org my-org --token <key>

# Or set environment variables
export RUNCONTEXT_ORG=my-org
export RUNCONTEXT_TOKEN=<key>
context publish