Skip to main content
Glama

Save access rules

save_access_rules
Destructive

Create a group's access rules on a connection (pass connectionId and groupId, or groupId null for everyone else), or replace an existing rule set's rules (pass id from list_access_rules). Send the complete rules: this replaces them rather than merging. Also needs the execute scope. Guard decides what AI tools, including you, may do on the team's databases, so change it only when the user asked for this exact change, and say what will change first. Needs an admin, the write scope, and an admin's approval in SaturnSQL for this AI tool: without it the call fails with code GUARD_APPROVAL_REQUIRED. Then call request_guard_edit, show the user the approvalUrl, and repeat the call after they approve. An approval lasts 12 hours; call end_guard_edit when the user's changes are done. Every change is recorded in SaturnSQL with the user's name.

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": {
      "tableAccess": "<tableAccess>",
      "tables": "<tables>",
      "hiddenColumns": "<hiddenColumns>",
      "maskedColumns": "<maskedColumns>",
      "rowFilters": "<rowFilters>"
    },
    "name": "save_access_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe rule set to replace. Omit to create one.
tablesYesTables for tableAccess only or except, as get_schema lists them.
groupIdNoWhen creating: the group, or null for everyone else.
rowFiltersYes
tableAccessYesall tables, only the listed tables, or all except the listed tables.
connectionIdNoWhen creating: the connection.
hiddenColumnsYesColumns as table.column.
maskedColumnsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag this as a destructive, non-read-only, non-open-world write, and the description substantially extends that: full replacement rather than merge, required execute/admin/write scopes, admin approval in SaturnSQL, the concrete failure code GUARD_APPROVAL_REQUIRED, a 12-hour approval lifetime, and per-user audit logging. Those are exactly the operational facts an agent cannot infer from the schema or hints.

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?

Front-loaded with the two operating modes, then the destructive warning, then the auth/approval procedure, which is the right priority order. It is dense and parenthetical, but nearly every clause carries distinct operational content; the approval-recovery sentence is long but each step earns its place.

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 an 8-parameter destructive write with no output schema, the description supplies the missing pieces: write mode, scoping, required permissions, the approval dance including the retry after approval, error code, approval expiry, cleanup call, and audit implications. Nothing an agent needs to invoke this safely is absent.

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 coverage is 75%, so the schema carries most parameter documentation, but the description adds real meaning: the id/connectionId/groupId parameter pairing encodes create-vs-replace, and 'Send the complete rules: this replaces them rather than merging' clarifies that all five required rule arrays must be supplied in full. Minor gap is that it does not touch rowFilters or maskedColumns semantics beyond what the schema already says.

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 ('Create a group's access rules on a connection') and explicitly covers the second mode, replacing an existing rule set. It distinguishes the two modes by parameter (connectionId/groupId vs id from list_access_rules), so an agent can tell which shape of call it is making 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 Guidelines5/5

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

Gives explicit when-to-call guidance ('change it only when the user asked for this exact change, and say what will change first') and names the workflow siblings: request_guard_edit for approval, the approvalUrl to show the user, and end_guard_edit when done. It also points to list_access_rules as the source of the id, so the create-vs-replace decision and the surrounding flow are both resolved.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources