ThinAir Data

configure_allowlist

Destructive

Manage HARD SQL guardrails for an enterprise connection: a TABLE ALLOWLIST (queries may reference only the listed tables — enforced at the AST level across subqueries/CTEs/JOINs) and a PII MASKING policy (mask flagged columns in query results). Both opt-out by default. action=view shows current policy + schema reference; set_tables replaces the allowlist (use [] to lock down everything); remove_allowlist disables it; set_pii_policy toggles masking + chooses which PII kinds to mask. Masking is a heuristic policy aid (not a compliance guarantee) and one-way per execution. [ENTERPRISE tier]

Input Schema

Name	Required	Description
`action`	Yes	What to do
`tables`	No	For set_tables: the allowlist. Bare ('users') or one-level schema-qualified ('public.users'). Empty array = lock down (no tables allowed).
`connection`	No	Target connection name from this tenant's inventory. Call `list_connections` to see every name + dialect. If the user didn't specify, use the tenant's default (first added). Do not invent names — resolve from `list_connections` output.
`pii_enabled`	No	For set_pii_policy: enable or disable result masking.
`mask_patterns`	No	For set_pii_policy: which PII kinds to mask (defaults to all when enabling without a list).

Output Schema

Name	Required	Description	Default
`data`	No
`meta`	No
`display`	No
`summary`	No
`insights`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedOct 31, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
changedOutput schema / additionalProperties
```
Previous value: -trueNew value: +{}
```

changedOutput schema / properties / data / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "type": "object"
-  },
-  {
-    "additionalProperties": true,
-    "properties": {
-      "code": {
-        "type": "string"
-      },
-      "details": {
-        "additionalProperties": {},
-        "type": "object"
-      },
-      "error": {
-        "type": "string"
-      },
-      "internal_code": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "retry_after_s": {
-        "type": "number"
-      },
-      "retryable": {
-        "type": "boolean"
-      }
-    },
-    "required": [
-      "error"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  {
+    "additionalProperties": {},
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "details": {
+        "additionalProperties": {},
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "error": {
+        "type": "string"
+      },
+      "internal_code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "retry_after_s": {
+        "type": "number"
+      },
+      "retryable": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

changedOutput schema / properties / display / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / display / properties / chart / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / display / properties / code / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / display / properties / map / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / display / properties / metric / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / insights / items / additionalProperties
```
Previous value: -trueNew value: +{}
```
changedOutput schema / properties / meta / additionalProperties
```
Previous value: -trueNew value: +{}
```
removedOutput schema / properties / meta / properties / rowCount / $ref
```
Removed value: -"#/properties/meta/properties/executionTimeMs"
```
addedOutput schema / properties / meta / properties / rowCount / type
```
Added value: +[
+  "number",
+  "string"
+]
```

Changed4 schema fields changedSep 30, 2026

changedOutput schema / properties / data / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "type": "object"
-  },
-  {
-    "additionalProperties": true,
-    "properties": {
-      "code": {
-        "type": "string"
-      },
-      "details": {
-        "additionalProperties": {},
-        "type": "object"
-      },
-      "error": {
-        "type": "string"
-      },
-      "internal_code": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "retry_after_s": {
-        "type": "number"
-      }
-    },
-    "required": [
-      "error"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "type": "object"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "details": {
+        "additionalProperties": {},
+        "type": "object"
+      },
+      "error": {
+        "type": "string"
+      },
+      "internal_code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "retry_after_s": {
+        "type": "number"
+      },
+      "retryable": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

addedOutput schema / properties / meta / properties / maskedCells
```
Added value: +{
+  "type": "number"
+}
```

addedOutput schema / properties / meta / properties / maskedColumns

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / meta / properties / rowCapReached
```
Added value: +{
+  "type": "boolean"
+}
```

Changed1 schema field changedSep 15, 2026

changedOutput schema / properties / data / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "type": "object"
-  },
-  {
-    "additionalProperties": true,
-    "properties": {
-      "code": {
-        "type": "string"
-      },
-      "details": {
-        "additionalProperties": {},
-        "type": "object"
-      },
-      "error": {
-        "type": "string"
-      },
-      "internal_code": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "retry_after_s": {
-        "type": "number"
-      }
-    },
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "type": "object"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "details": {
+        "additionalProperties": {},
+        "type": "object"
+      },
+      "error": {
+        "type": "string"
+      },
+      "internal_code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "retry_after_s": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

AddedAug 17, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past the destructiveHint=true annotation: it explains that set_tables fully replaces the allowlist, that [] locks everything down, that masking is one-way per execution, and that the masking is a heuristic aid rather than a compliance guarantee. Those caveats tell the agent exactly what state is overwritten and what the tool cannot promise.

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?

Dense and front-loaded: the two guardrails come first, then action semantics, then caveats, with no filler. It is on the long side for a single paragraph, but each clause carries real policy detail.

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?

With an output schema, fully described parameters, and destructive/enterprise annotations, the description covers everything needed to select and invoke it correctly, including tier gating and the irreversibility of masking.

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 100% and every parameter already carries a description, including the table format and PII enum. The description reinforces the action semantics and [] meaning but adds little the schema does not already state, so the baseline 3 applies.

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 (manage hard SQL guardrails on an enterprise connection) and enumerates the two mechanisms, a table allowlist enforced at the AST level and a PII masking policy, then names each action. An agent can distinguish this policy-configuration tool from query-execution siblings like query_sql or pii_scan without opening the schema.

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?

Gives per-action guidance for all four enum values (view shows policy, set_tables replaces, remove_allowlist disables, set_pii_policy toggles masking), plus the opt-out default and the [] lockdown trick. It stops short of naming sibling alternatives or explicit when-not-to-use exclusions, so a 4 rather than a 5.

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

All ThinAir Data 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?