Skip to main content
Glama
Sign In

AI SENSE Free Public Tools

by com.aisenseapi
OverviewDiscussionsAdmin

Create an agent run

create_agent_run

Create a run: a plan of 1 to 16 steps that the service keeps and goes through in order, with its deadlines and recovery, for up to 24 hours. Version 1 uses external workers. Version 2 uses an AI SENSE managed executor with your OpenAI or Ollama Cloud model, bounded tools and a fixed lifetime. Managed mode requires separate credential installation by direct HTTPS POST /services/v1/run/{run_id}/credentials using the control token; never put provider keys, Telegram tokens, or private Slack or Discord webhook URLs in MCP arguments, steps or Storage. Managed creation waits for credentials and may answer unavailable until this mode is enabled. A step is delegate, a job workers claim through claim_agent_queue_job in version 1; wait, on time, a person or an external signal in version 1, or time or an owned action form in version 2; decide, rules over the last result; and complete, always the last one. Returns run_id, read_token and control_token once, and only in version 1 with delegated steps queue_id and worker_token for the workers. With idempotency_key, a repeat after a lost answer returns the same run and tokens instead of a new run. Creation allows 20 per IP per UTC day. No API key, no account and no sign up.

Input Schema

NameRequiredDescriptionDefault
stepsYesEach step has id and type. delegate takes task and timeout_seconds. Managed delegates can require_tools and require_artifacts. Optional store_result_as reserves a handle for a Storage result created in that step. It needs storage_create and share_artifacts. Version 1 waits for time, external or human. Version 2 waits for time (delay_seconds or not_before_timestamp) or action (from_step, artifact, timeout_seconds, on_timeout:continue). After an action wait, a delegate requiring storage_create may set record_feedback:true. decide takes request and optional require. complete is last.
versionNoDefaults to 1 for external workers. Use 2 with execution for managed text-model execution.
executionNoManaged v2 configuration without credentials. Permissions restrict what the model may request. Tool results, not model claims, confirm effects.
ttl_secondsYesThe run's lifetime, fixed at creation and extended by nothing.
idempotency_keyNo32 bytes from a secure random source as lower-case hex, the same for a repeat of the same plan.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / execution / properties / permissions / properties / read_sources / description
      Added value: +"Up to four exact public HTTPS URLs or the slashdot_public feed. A query is part of the grant. Credentials, fragments, IP literals and private service addresses are refused."
    • removedInput schema / properties / execution / properties / permissions / properties / read_sources / items / enum
      Removed value: -[
-  "slashdot_public"
-]
    • addedInput schema / properties / execution / properties / permissions / properties / read_sources / items / maxLength
      Added value: +1024
    • changedInput schema / properties / execution / properties / permissions / properties / read_sources / maxItems
      Previous value: -1New value: +4
    • addedInput schema / properties / execution / properties / permissions / properties / read_sources / uniqueItems
      Added value: +true
    • addedInput schema / properties / execution / properties / tools / description
      Added value: +"Choose at most one delivery tool. Delivery needs share_artifacts permission and the channel credentials installed over HTTPS."
    • changedInput schema / properties / execution / properties / tools / items / enum
      Previous value: -[
-  "web_read",
-  "storage_create",
-  "storage_read",
-  "action_create",
-  "action_read",
-  "telegram_send"
-]New value: +[
+  "web_read",
+  "storage_create",
+  "storage_read",
+  "action_create",
+  "action_read",
+  "telegram_send",
+  "slack_send",
+  "discord_send"
+]
    • changedInput schema / properties / steps / description
      Previous value: -"Each step has id and type. delegate takes task and timeout_seconds; managed delegates can require_tools and require_artifacts. Version 1 waits for time, external or human. Version 2 waits for time (delay_seconds or not_before_timestamp) or action (from_step, artifact, timeout_seconds, on_timeout:continue). After an action wait, a delegate requiring storage_create may set record_feedback:true. decide takes request and optional require. complete is last."New value: +"Each step has id and type. delegate takes task and timeout_seconds. Managed delegates can require_tools and require_artifacts. Optional store_result_as reserves a handle for a Storage result created in that step. It needs storage_create and share_artifacts. Version 1 waits for time, external or human. Version 2 waits for time (delay_seconds or not_before_timestamp) or action (from_step, artifact, timeout_seconds, on_timeout:continue). After an action wait, a delegate requiring storage_create may set record_feedback:true. decide takes request and optional require. complete is last."
  2. Changed3 schema fields changed
    • addedInput schema / properties / execution
      Added value: +{
+  "additionalProperties": false,
+  "description": "Managed v2 configuration without credentials. Permissions restrict what the model may request. Tool results, not model claims, confirm effects.",
+  "properties": {
+    "limits": {
+      "additionalProperties": false,
+      "properties": {
+        "model_calls": {
+          "maximum": 16,
+          "minimum": 1,
+          "type": "integer"
+        },
+        "tool_calls": {
+          "maximum": 32,
+          "minimum": 0,
+          "type": "integer"
+        },
+        "web_reads": {
+          "maximum": 12,
+          "minimum": 0,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "model_calls",
+        "tool_calls",
+        "web_reads"
+      ],
+      "type": "object"
+    },
+    "mode": {
+      "enum": [
+        "managed"
+      ],
+      "type": "string"
+    },
+    "model": {
+      "maxLength": 160,
+      "minLength": 1,
+      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:/-]{0,159}$",
+      "type": "string"
+    },
+    "permissions": {
+      "additionalProperties": false,
+      "properties": {
+        "read_sources": {
+          "items": {
+            "enum": [
+              "slashdot_public"
+            ],
+            "type": "string"
+          },
+          "maxItems": 1,
+          "minItems": 0,
+          "type": "array"
+        },
+        "share_artifacts": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "read_sources",
+        "share_artifacts"
+      ],
+      "type": "object"
+    },
+    "protocol": {
+      "enum": [
+        "text_protocol"
+      ],
+      "type": "string"
+    },
+    "provider": {
+      "enum": [
+        "openai",
+        "ollama_cloud"
+      ],
+      "type": "string"
+    },
+    "tools": {
+      "items": {
+        "enum": [
+          "web_read",
+          "storage_create",
+          "storage_read",
+          "action_create",
+          "action_read",
+          "telegram_send"
+        ],
+        "type": "string"
+      },
+      "maxItems": 6,
+      "minItems": 0,
+      "type": "array",
+      "uniqueItems": true
+    }
+  },
+  "required": [
+    "mode",
+    "provider",
+    "model",
+    "protocol",
+    "tools",
+    "permissions",
+    "limits"
+  ],
+  "type": "object"
+}
    • changedInput schema / properties / steps / description
      Previous value: -"The steps in order. Each has id and type. delegate takes task and timeout_seconds, wait takes event (time, external or human) with delay_seconds or timeout_seconds, decide takes request with state and questions, and optional require."New value: +"Each step has id and type. delegate takes task and timeout_seconds; managed delegates can require_tools and require_artifacts. Version 1 waits for time, external or human. Version 2 waits for time (delay_seconds or not_before_timestamp) or action (from_step, artifact, timeout_seconds, on_timeout:continue). After an action wait, a delegate requiring storage_create may set record_feedback:true. decide takes request and optional require. complete is last."
    • addedInput schema / properties / version
      Added value: +{
+  "description": "Defaults to 1 for external workers. Use 2 with execution for managed text-model execution.",
+  "enum": [
+    1,
+    2
+  ],
+  "type": "integer"
+}
  3. Added

TDQS

Score is being calculated.

All AI SENSE Free Public Tools toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources