StreamClipping AI

StreamClipping AI account status

get_account

Read-only

Current plan, available processing minutes, remaining magic clipping quota, Credits balance (credits field, read only) and connected social accounts. An import fails when minutes run short. During the free trial, the quota is one hour of video PER DAY, refilled at midnight local time (trialDaily field).

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`plan`	Yes	Effective plan: FREE, CREATOR, PRO or ELITE. During the trial, this is the trial plan.
`trial`	Yes	Current trial. `active` is false when the organization is not on a trial.
`appUrl`	Yes	Web app address, for actions that are handled there.
`credits`	Yes	Credits wallet, read only. Beyond the monthly quota of the plan, one Credit pays for one magic project, one dubbing or one editor render. null when Credits are not offered to this account and its balance is zero, or when the balance could not be read.
`minutes`	Yes	Minutes wallet. One minute is consumed per minute of source video processed, not per clip produced.
`paidPlan`	Yes	Plan on the account, trial excluded. A gifted ambassador plan also appears here; whether X publishing is allowed is given by canPublishHere in list_social_accounts.
`retestPass`	Yes	Two-video pass: a one-time purchase that gives back the trial features for 2 new videos (up to 1 hour each), no live. Not a trial and not a subscription: nothing is charged when it ends.
`trialDaily`	Yes	Free trial only: one hour of video per day, not cumulative, refilled at midnight local time. null outside the free trial. When the day's minutes run out, the options are waiting for the refill or moving to a paid plan.
`magicClipping`	Yes	Magic clipping: fully automatic detection and editing.
`socialAccounts`	Yes	Connected social accounts. Publishing requires an ACTIVE account. TWITCH is only used for importing, never for publishing. Publishing on X (TWITTER) requires a paid Pro or Elite plan.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 24, 2026

addedOutput schema / properties / credits

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "balance": {
+          "description": "Credits in the organization wallet.",
+          "type": "number"
+        },
+        "canBuy": {
+          "description": "True when this account can buy Credits, from the store of the web app (appUrl). They cannot be bought here.",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "balance",
+        "canBuy"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Credits wallet, read only. Beyond the monthly quota of the plan, one Credit pays for one magic project, one dubbing or one editor render. null when Credits are not offered to this account and its balance is zero, or when the balance could not be read."
+}

changedOutput schema / properties / magicClipping / properties / remaining / description

Previous value: -"Magic projects left this month."New value: +"Magic projects that can still be started: what is left of the monthly quota, plus bought Magic and Credits."

changedOutput schema / required

Previous value: -[
-  "plan",
-  "paidPlan",
-  "trial",
-  "retestPass",
-  "minutes",
-  "trialDaily",
-  "magicClipping",
-  "socialAccounts",
-  "appUrl"
-]New value: +[
+  "plan",
+  "paidPlan",
+  "trial",
+  "retestPass",
+  "minutes",
+  "trialDaily",
+  "magicClipping",
+  "credits",
+  "socialAccounts",
+  "appUrl"
+]

Changed2 schema fields changedOct 11, 2026

addedOutput schema / properties / retestPass

Added value: +{
+  "additionalProperties": false,
+  "description": "Two-video pass: a one-time purchase that gives back the trial features for 2 new videos (up to 1 hour each), no live. Not a trial and not a subscription: nothing is charged when it ends.",
+  "properties": {
+    "active": {
+      "type": "boolean"
+    },
+    "daysLeft": {
+      "type": [
+        "number",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "active",
+    "daysLeft"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "plan",
-  "paidPlan",
-  "trial",
-  "minutes",
-  "trialDaily",
-  "magicClipping",
-  "socialAccounts",
-  "appUrl"
-]New value: +[
+  "plan",
+  "paidPlan",
+  "trial",
+  "retestPass",
+  "minutes",
+  "trialDaily",
+  "magicClipping",
+  "socialAccounts",
+  "appUrl"
+]

First observedOct 9, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a safe read-only, closed-world operation, so the description is free to add the non-obvious semantics: the import failure mode when minutes are exhausted and the trial quota resetting at midnight local time in the trialDaily field. It does not cover auth or freshness of the counters, but the operational caveats it does provide are genuinely additive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It front-loads the list of returned values, then adds two short caveat sentences about quota behaviour. Nothing is redundant, though the field enumeration reads as a run-on list rather than a scannable structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read tool with an output schema and readOnly annotations, the description supplies everything an agent needs: what is returned, the read-only nature of credits, and the quota reset rule. Return-value structure is left to the output schema, which is correct.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero input parameters, so the baseline is 4. The description does useful extra work by naming the specific response fields (credits, trialDaily) and flagging that credits is read-only, which aids interpretation of the output.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource — the account's plan, minutes, magic-clipping quota, credits and connected social accounts — so an agent knows exactly what it gets back. It does not explicitly contrast with siblings like get_analytics or list_social_accounts, even though 'connected social accounts' overlaps with the latter, so differentiation is only implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The line 'An import fails when minutes run short' implies a pre-flight check before import_vod, which is a useful usage cue, but it is never framed as 'call this before X' and no alternative tools are named or excluded. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All StreamClipping AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?