Scale AI · Schema

CreateAgentConfigRequest

Data EngineLabelingRLHFGenAI PlatformDonovanDefense AILiDARSensor FusionREST API

Properties

Name Type Description
name string
description string
system_prompt string
harness object Harness strategy. See Harness enum for supported values.
allowed_tools array Tools enabled for this config. See AllowedTool enum for the catalogue.
model string
persistent_workspace boolean Give tasks a persistent /workspace that survives sandbox death. Fixed for a task's life; defaults off.
repos array Per-config repo override. None uses the deployment default; an empty list clones nothing.
View JSON Schema on GitHub

JSON Schema

scale-ai-create-agent-config-request-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/scale-ai/json-schema/scale-ai-create-agent-config-request-schema.json",
  "title": "CreateAgentConfigRequest",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/scale-ai-agent-configs-api-openapi.yml#/components/schemas/CreateAgentConfigRequest",
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 255,
      "minLength": 1,
      "title": "Name"
    },
    "description": {
      "title": "Description",
      "type": "string",
      "maxLength": 2000
    },
    "system_prompt": {
      "type": "string",
      "maxLength": 100000,
      "minLength": 1,
      "title": "System Prompt"
    },
    "harness": {
      "$ref": "#/$defs/Harness",
      "description": "Harness strategy. See Harness enum for supported values."
    },
    "allowed_tools": {
      "items": {
        "$ref": "#/$defs/AllowedTool"
      },
      "type": "array",
      "title": "Allowed Tools",
      "description": "Tools enabled for this config. See AllowedTool enum for the catalogue."
    },
    "model": {
      "type": "string",
      "maxLength": 255,
      "minLength": 1,
      "title": "Model"
    },
    "persistent_workspace": {
      "type": "boolean",
      "title": "Persistent Workspace",
      "description": "Give tasks a persistent /workspace that survives sandbox death. Fixed for a task's life; defaults off.",
      "default": false
    },
    "repos": {
      "title": "Repos",
      "description": "Per-config repo override. None uses the deployment default; an empty list clones nothing.",
      "items": {
        "$ref": "#/$defs/RepoSpec"
      },
      "type": "array"
    }
  },
  "type": "object",
  "required": [
    "name",
    "system_prompt",
    "harness",
    "model"
  ],
  "$defs": {
    "AllowedTool": {
      "type": "string",
      "enum": [
        "Read",
        "Write",
        "Edit",
        "Bash",
        "Glob",
        "Grep",
        "List",
        "WebFetch",
        "WebSearch",
        "Task",
        "TodoWrite",
        "NotebookEdit",
        "ExitPlanMode",
        "Slack",
        "Linear",
        "GitHub",
        "Confluence",
        "Notion",
        "Datadog",
        "PagerDuty",
        "Salesforce",
        "Figma",
        "Granola",
        "Jira",
        "Gmail",
        "GoogleCalendar",
        "GoogleDrive",
        "GoogleDocs",
        "GoogleSheets",
        "GoogleSlides",
        "Snowflake",
        "Redash",
        "Tableau",
        "Metabase",
        "Gong",
        "ZoomInfo",
        "Clay"
      ],
      "title": "AllowedTool",
      "description": "Tools an agent config may be granted.\n\nGranting an MCP server name (Slack, Linear, etc.) authorizes every tool\nexposed by that server, scoped via the agent's credentials."
    },
    "Harness": {
      "type": "string",
      "enum": [
        "claude-code",
        "codex",
        "litellm"
      ],
      "title": "Harness",
      "description": "Supported agent harness strategies.\n\nMirrors ``PROVIDERS`` in golden-agent's ``project/harness/activity.py``."
    },
    "RepoSpec": {
      "properties": {
        "url": {
          "type": "string",
          "maxLength": 2048,
          "minLength": 1,
          "title": "Url"
        },
        "path": {
          "title": "Path",
          "type": "string",
          "maxLength": 1024
        },
        "depth": {
          "title": "Depth",
          "type": "integer",
          "minimum": 1
        }
      },
      "type": "object",
      "required": [
        "url"
      ],
      "title": "RepoSpec",
      "description": "A single repo the agent should clone into its workspace.\n\nMirrors the per-entry shape the golden agent's ``_validate_repos`` accepts:\n``url`` is required, the rest are optional passthrough hints. Sent verbatim\nas ``task.params.repos`` so provisioning clones these instead of the\ndeployment-global default."
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/scale-ai-create-agent-config-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.