KnowJudges

find_ai_abuse_cases

Read-only

Find reported AI-related legal-error cases, including fabricated citations and authorities. Use query for a case name, error type, or outcome; response distinguishes sanctions from no sanctions. Optional court, judge, state, and date filters narrow results. Returns at most 10 cases with verified decision links or labeled source fallbacks. Describe recorded allegations and outcomes; dataset inclusion alone does not establish a judicial finding of AI use. Empty and bulk searches are unavailable.

Input Schema

TableJSON Schema

Name	Required	Description
`court`	No	Court name fragment
`judge`	No	Judge name fragment
`limit`	No	Maximum results, capped at 10
`query`	No	Case name, error type, ruling text, court, state, or judge search text
`state`	No	US state name
`to_date`	No	Inclusive latest decision date
`response`	No	Court response, for example Warning or Sanctions
`from_date`	No	Inclusive earliest decision date

Output Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	Yes
`filters`	Yes
`results`	Yes
`public_access`	Yes
`total_matches`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 8, 2026

addedOutput schema / properties / results / items / properties / rulings / description

Added value: +"Unavailable unless a decision count is documented; judge links are not a ruling count."

addedOutput schema / properties / results / items / properties / summary_note

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

Changed17 schema fields changedOct 7, 2026
- addedOutput schema / properties / results / items / properties / court / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / court / type
```
Removed value: -"string"
```
- addedOutput schema / properties / results / items / properties / court_response / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / court_response / type
```
Removed value: -"string"
```
- addedOutput schema / properties / results / items / properties / decision_date / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / decision_date / type
```
Removed value: -"string"
```
- addedOutput schema / properties / results / items / properties / decision_url / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / decision_url / type
```
Removed value: -"string"
```
- addedOutput schema / properties / results / items / properties / rulings / anyOf
```
Added value: +[
+  {
+    "maximum": 9007199254740991,
+    "minimum": 0,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / rulings / maximum
```
Removed value: -9007199254740991
```
- removedOutput schema / properties / results / items / properties / rulings / minimum
```
Removed value: -0
```
- removedOutput schema / properties / results / items / properties / rulings / type
```
Removed value: -"integer"
```
- addedOutput schema / properties / results / items / properties / state / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / state / type
```
Removed value: -"string"
```
- addedOutput schema / properties / results / items / properties / summary / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- removedOutput schema / properties / results / items / properties / summary / type
```
Removed value: -"string"
```
- changedOutput schema / properties / results / items / required
```
Previous value: -[
-  "case_name",
-  "decision_date",
-  "court",
-  "state",
-  "court_response",
-  "summary",
-  "rulings",
-  "judges",
-  "decision_url",
-  "decision_link_status",
-  "directory_url",
-  "dataset_source"
-]New value: +[
+  "case_name",
+  "judges",
+  "decision_link_status",
+  "directory_url",
+  "dataset_source"
+]
```

Changed10 schema fields changedOct 7, 2026

removedOutput schema / properties / public_access / properties / quota_shared_across

Removed value: -{
-  "prefixItems": [
-    {
-      "const": "api",
-      "type": "string"
-    },
-    {
-      "const": "mcp",
-      "type": "string"
-    }
-  ],
-  "type": "array"
-}

removedOutput schema / properties / public_access / properties / requests_per_day
```
Removed value: -{
-  "const": 100,
-  "type": "number"
-}
```
removedOutput schema / properties / public_access / properties / requests_per_hour
```
Removed value: -{
-  "const": 20,
-  "type": "number"
-}
```

changedOutput schema / properties / public_access / required

Previous value: -[
-  "maximum_results_per_request",
-  "requests_per_hour",
-  "requests_per_day",
-  "quota_shared_across"
-]New value: +[
+  "maximum_results_per_request"
+]

removedOutput schema / properties / results / items / properties / decision_link_status / enum
```
Removed value: -[
-  "source_fallback",
-  "verified"
-]
```
removedOutput schema / properties / results / items / properties / decision_link_type
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / properties / results / items / properties / id
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / properties / results / items / properties / judges / items / properties / slug
```
Removed value: -{
-  "type": "string"
-}
```

changedOutput schema / properties / results / items / properties / judges / items / required

Previous value: -[
-  "slug",
-  "name",
-  "profile_url"
-]New value: +[
+  "name",
+  "profile_url"
+]

changedOutput schema / properties / results / items / required

Previous value: -[
-  "id",
-  "case_name",
-  "decision_date",
-  "court",
-  "state",
-  "court_response",
-  "summary",
-  "rulings",
-  "judges",
-  "decision_url",
-  "decision_link_type",
-  "decision_link_status",
-  "directory_url",
-  "dataset_source"
-]New value: +[
+  "case_name",
+  "decision_date",
+  "court",
+  "state",
+  "court_response",
+  "summary",
+  "rulings",
+  "judges",
+  "decision_url",
+  "decision_link_status",
+  "directory_url",
+  "dataset_source"
+]

Changed1 schema field changedOct 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "filters": {
+      "additionalProperties": false,
+      "properties": {
+        "court": {
+          "type": "string"
+        },
+        "from_date": {
+          "type": "string"
+        },
+        "judge": {
+          "type": "string"
+        },
+        "query": {
+          "type": "string"
+        },
+        "response": {
+          "type": "string"
+        },
+        "state": {
+          "type": "string"
+        },
+        "to_date": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "limit": {
+      "maximum": 10,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "public_access": {
+      "additionalProperties": false,
+      "properties": {
+        "maximum_results_per_request": {
+          "const": 10,
+          "type": "number"
+        },
+        "quota_shared_across": {
+          "prefixItems": [
+            {
+              "const": "api",
+              "type": "string"
+            },
+            {
+              "const": "mcp",
+              "type": "string"
+            }
+          ],
+          "type": "array"
+        },
+        "requests_per_day": {
+          "const": 100,
+          "type": "number"
+        },
+        "requests_per_hour": {
+          "const": 20,
+          "type": "number"
+        }
+      },
+      "required": [
+        "maximum_results_per_request",
+        "requests_per_hour",
+        "requests_per_day",
+        "quota_shared_across"
+      ],
+      "type": "object"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "case_name": {
+            "type": "string"
+          },
+          "court": {
+            "type": "string"
+          },
+          "court_response": {
+            "type": "string"
+          },
+          "dataset_source": {
+            "additionalProperties": false,
+            "properties": {
+              "name": {
+                "type": "string"
+              },
+              "url": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "name",
+              "url"
+            ],
+            "type": "object"
+          },
+          "decision_date": {
+            "type": "string"
+          },
+          "decision_link_status": {
+            "enum": [
+              "source_fallback",
+              "verified"
+            ],
+            "type": "string"
+          },
+          "decision_link_type": {
+            "type": "string"
+          },
+          "decision_url": {
+            "type": "string"
+          },
+          "directory_url": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "judges": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "profile_url": {
+                  "type": "string"
+                },
+                "slug": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "slug",
+                "name",
+                "profile_url"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "rulings": {
+            "maximum": 9007199254740991,
+            "minimum": 0,
+            "type": "integer"
+          },
+          "state": {
+            "type": "string"
+          },
+          "summary": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "case_name",
+          "decision_date",
+          "court",
+          "state",
+          "court_response",
+          "summary",
+          "rulings",
+          "judges",
+          "decision_url",
+          "decision_link_type",
+          "decision_link_status",
+          "directory_url",
+          "dataset_source"
+        ],
+        "type": "object"
+      },
+      "maxItems": 10,
+      "type": "array"
+    },
+    "total_matches": {
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "filters",
+    "limit",
+    "total_matches",
+    "results",
+    "public_access"
+  ],
+  "type": "object"
+}

First observedAug 17, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish a safe read operation, but the description adds real behavioral context beyond them: a hard cap of 10 results, how decision links are returned (verified links or labeled fallbacks), and the important caveat that dataset inclusion is not a judicial finding of AI use. It does not discuss rate limits or latency, so not a 5.

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?

Four front-loaded sentences that each carry information (scope, query usage, filter behavior, return shape) with minimal waste. Slightly dense mid-paragraph but still efficient.

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?

For an 8-parameter read-only search tool with an output schema, the description covers scope, result cap, link handling, and the judicial-finding caveat, which is enough to call it correctly. The only missing nuance is guidance on combining filters, a minor gap.

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 description coverage is 100%, so the schema already documents all eight parameters including the limit cap and date bounds. The description adds that court/judge/state/date filters 'narrow' results and that response distinguishes sanctions from no sanctions, but adds no syntax or format detail beyond the schema.

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

Purpose5/5

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

States a specific verb and resource ('Find reported AI-related legal-error cases, including fabricated citations and authorities') with scope that no sibling (find_court, find_judges) shares. An agent can distinguish this tool from the other find_* tools immediately.

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?

Explains how to drive the search ('Use query for a case name, error type, or outcome') and names the optional narrowing filters, plus explicitly rules out empty and bulk searches. It stops short of naming a specific sibling alternative when a different tool would be better, so it falls just under 5.

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

All KnowJudges 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.