Skip to main content
Glama

ThinAir Data

by co.thinair.data
OverviewDiscussionsAdmin

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

TableJSON Schema
NameRequiredDescriptionDefault
actionYesWhat to do
tablesNoFor set_tables: the allowlist. Bare ('users') or one-level schema-qualified ('public.users'). Empty array = lock down (no tables allowed).
connectionNoTarget 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_enabledNoFor set_pii_policy: enable or disable result masking.
mask_patternsNoFor set_pii_policy: which PII kinds to mask (defaults to all when enabling without a list).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
metaNo
displayNo
summaryNo
insightsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • 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"
+  }
+]
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Adds substantial behavioral context beyond annotations: opt-out by default, AST-level enforcement across subqueries/CTEs/JOINs, one-way masking, and heuristic (non-compliance) nature. Also notes that [] locks down everything. No contradiction with destructiveHint=true.

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

Conciseness5/5

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

Dense but well-structured: overview of the two guardrails, then explicit action list with usage, then a critical caveat. Every sentence earns its place with no filler or repetition.

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 tool with 5 parameters and multiple actions, the description covers all actions, their effects, key caveats (opt-out, one-way, heuristic), and AST enforcement. Output schema handles return values, so that is not needed. Combined with rich schema and annotations, it is complete.

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?

Schema has 100% coverage with detailed parameter descriptions, so baseline is 3. The main description adds cross-references (which action uses which parameter) and the one-way masking caveat, providing additional semantic context 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 ('Manage') and resource ('HARD SQL guardrails for an enterprise connection'), then details the two policies (TABLE ALLOWLIST and PII MASKING) and lists concrete actions. It clearly differentiates from siblings like query_firewall or pii_scan by focusing on allowlist/PII policy configuration.

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?

Provides clear context for each action (view, set_tables, remove_allowlist, set_pii_policy) and explains when to use them. However, it does not explicitly mention alternatives or when NOT to use this tool versus siblings like pii_scan or query_firewall, so it lacks explicit exclusions.

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

All ThinAir Data toolsInspect
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