Rightshold

Check many inputs at once

check_rights_batch

Call before shipping anything that bundles third-party assets. Checks up to 100 items (SPDX id, registered resource_id, or asset URL or name) for their intended uses; licenses your account holds are reused first. Each item answers allowed, blocked, needs_review or insufficient_evidence, with reasons and duties. Free, no key. Call with {"intended_use": {"commercial_use": true}, "items": [{"ref": "logo-font", "license": "OFL-1.1"}, {"ref": "hero-photo", "license": "CC-BY-NC-4.0"}]}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "items": "<items>"
    },
    "name": "check_rights_batch"
  }
}

Input Schema

Name	Required	Description	Default
`items`	Yes
`intended_use`	No	Uses to check: each true flag must be documented; omitted = false; unknown fields refused. For instance {"commercial_use":true}

Output Schema

Name	Required	Description	Default
`items`	Yes
`summary`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 20, 2026

removedInput schema / properties / api_key

Removed value: -{
-  "deprecated": true,
-  "description": "Deprecated: use Authorization: Bearer <key>. With a key the assessment is kept in your account.",
-  "type": "string"
-}

changedInput schema / properties / intended_use / description

Previous value: -"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Uses to check: each true flag must be documented; omitted = false; unknown fields refused. For instance {\"commercial_use\":true}"

addedInput schema / properties / items / items / properties / asset / description
```
Added value: +"URL or name"
```

changedInput schema / properties / items / items / properties / intended_use / description

Previous value: -"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Uses to check: each true flag must be documented; omitted = false; unknown fields refused. For instance {\"commercial_use\":true}"

addedInput schema / properties / items / items / properties / license / description
```
Added value: +"SPDX id"
```
addedInput schema / properties / items / items / properties / ref / description
```
Added value: +"Your label"
```

Changed4 schema fields changedOct 18, 2026

addedInput schema / properties / api_key / deprecated
```
Added value: +true
```

changedInput schema / properties / api_key / description

Previous value: -"Optional: your Rightshold API key, so the assessment is kept in your own account (otherwise it is kept in the public workspace). Not needed if your MCP client sends Authorization: Bearer <key>."New value: +"Deprecated: use Authorization: Bearer <key>. With a key the assessment is kept in your account."

changedInput schema / properties / intended_use / description

Previous value: -"Intended use. Every true flag is a right the assessment must find documented; omitted flags are false. Unknown fields are refused (invalid_intended_use). For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"

changedInput schema / properties / items / items / properties / intended_use / description

Previous value: -"Intended use. Every true flag is a right the assessment must find documented; omitted flags are false. Unknown fields are refused (invalid_intended_use). For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"

Changed2 schema fields changedOct 17, 2026

addedOutput schema / properties

Added value: +{
+  "items": {
+    "items": {
+      "properties": {
+        "answer": {
+          "enum": [
+            "allowed",
+            "blocked",
+            "needs_review",
+            "insufficient_evidence"
+          ]
+        },
+        "duties": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "ref",
+        "answer"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "summary": {
+    "properties": {
+      "all_clear": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "total",
+      "all_clear"
+    ],
+    "type": "object"
+  }
+}

addedOutput schema / required

Added value: +[
+  "items",
+  "summary"
+]

Changed1 schema field changedOct 14, 2026
- changedOutput schema / (root)
```
Previous value: -nullNew value: +{
+  "type": "object"
+}
```
First observedOct 12, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The description adds real context beyond the annotations: 'Free, no key', that licenses already held are reused first, and that each item returns one of four verdicts with reasons and duties. However, annotations declare readOnlyHint=false and idempotentHint=false, and the description never explains why a check is not read-only or what makes repeated calls non-idempotent — a notable gap for an agent that might retry.

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?

The pre-shipping trigger leads, followed by scope, then the result vocabulary, then the example — a sensible front-loaded order with near-zero filler. The inline JSON example is slightly long but earns its place by pinning down item structure.

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

Completeness4/5

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

With an output schema present, the description need not explain return values, yet it usefully names the four verdict categories and notes that reasons and duties accompany them. Remaining gaps are edge behavior: what happens beyond 100 items, whether partial failures are reported per item, and how duplicate refs are handled.

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

Parameters3/5

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

Schema coverage is 50%, and the description compensates partially by explaining the three accepted item identifier forms and the 100-item cap. The embedded example also demonstrates per-item licensing and the intended_use shape. It does not clarify how a per-item intended_use interacts with the top-level one, which is the main semantic ambiguity left.

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?

States a specific verb and resource ('Checks up to 100 items ... for their intended uses') and enumerates the acceptable item identifiers (SPDX id, resource_id, asset URL or name). The batch scope and the four outcome states make it distinguishable from a single-item license check, though no sibling is named explicitly.

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

Usage Guidelines4/5

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

'Call before shipping anything that bundles third-party assets' gives a concrete trigger condition and is front-loaded. It stops short of routing the agent between this, check_license, and assess_resource_for_use when only one item is at stake, so the batch-vs-single choice is inferred 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 Rightshold 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?