Skip to main content
Glama

get_agent_access_matrix

Read-only

Shows who can run each AI agent by listing its execute ACLs, roles, active/A2A status, run-as user, and role masking, and flags agents missing execute ACLs so deny-by-default access gaps are visible.

Instructions

Who can run each AI agent: its execute ACLs (type gen_ai_agent, falling back to the "*" wildcard rule), the roles on them (flagging roles that do not exist), whether the agent is active and exposed over A2A, its run-as user, and its role masking (sys_agent_access_role_configuration). Agents with no execute ACL of their own are flagged, because Brazil makes AI agent access deny-by-default. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_agent_access_matrix"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoAgent name contains
limitNoMax agents (default 50, max 300)
gaps_onlyNoOnly agents with a gap: wildcard or no execute ACL, open to any signed-in user, or missing roles
active_onlyNoOnly active agents (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real behavior beyond them: the fallback from agent-specific execute ACLs to the "*" wildcard rule, flagging of roles that do not exist, flagging of agents with no ACL because access is deny-by-default, and the sys_agent_access_role_configuration source. It omits result shape and pagination details, 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?

It is a single front-loaded sentence that leads with the core question 'Who can run each AI agent' and then enumerates what is returned, ending with the read-only marker. It is dense and slightly run-on, but no sentence is wasted.

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?

There is no output schema, so the description carries the return-value burden and does so by enumerating ACLs, role validation, active/A2A status, run-as user, and masking. Given four optional filters and no destructive behavior, an agent has enough to call it correctly; only pagination/ordering conventions are unstated.

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 100%, so the baseline is 3, but the description adds meaning the schema does not: it explains why the wildcard rule matters and why an agent with no execute ACL is treated as a gap (deny-by-default), which gives gaps_only concrete semantics. The remaining parameters (name, limit, active_only) are left entirely to the schema.

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?

The description states a specific resource and scope: execute ACLs on AI agents, including roles, active/A2A exposure, run-as user, and role masking. An agent can tell this is an access-posture report rather than a generic ACL fetch like get_acl. It stops short of naming a sibling alternative for the adjacent question (e.g. actually testing access), so it lands at 4 rather than 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the deny-by-default rationale and the gap flagging suggest auditing agents for missing ACLs, and gaps_only reinforces that. There is no explicit 'use this when... instead of test_agent_access / get_acl' routing and no statement of preconditions or when not to use it.

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

Deploy Server

Other Tools