Skip to main content
Glama

get_mcp_exposure

Read-only

Retrieve a read-only inventory of MCP servers, exposed tools, external registries, A2A agents, OAuth clients, roles, and agent properties to audit AI exposure and flag write-capable tools.

Instructions

What the instance exposes to outside AI and what outside AI it calls: MCP Server Console servers and their tools (with tools that look write-capable flagged), the external MCP server registry, A2A-exposed agents, external agent providers, OAuth clients that can reach them (token format, grant type), MCP roles and the agent MCP and external agent properties. 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_mcp_exposure"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax rows per list (default 50)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.1.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description's 'Read-only' merely restates that. It does add useful behavioral detail beyond the annotations: tools that look write-capable are flagged, and OAuth client data includes token format and grant type. It says nothing, however, about how the multiple lists are bounded or whether sections are truncated.

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

Conciseness3/5

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

It is a single dense sentence built around a long colon-delimited list, with no internal structure or grouping. Every item earns its place as returned content, but the wall-of-items form makes it harder to scan than a short lead sentence plus grouped bullets would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the enumeration of returned sections is doing real work and is the right instinct for an aggregate read tool. It is still incomplete on the operational side: pagination across multiple lists, result size, and how the write-capable flag is presented are all unaddressed.

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?

There is a single optional parameter with 100% schema description coverage ('Max rows per list (default 50)'), so the schema carries the semantics. The description adds nothing about the limit, and in particular does not clarify that the cap applies per list across several enumerated lists.

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 names concrete resources: MCP Server Console servers and tools, the external MCP server registry, A2A-exposed agents, external agent providers, OAuth clients, MCP roles and agent properties. It is an aggregate/exposure-inventory tool, but the verb is implicit ('what the instance exposes') rather than a stated action, and it never says how it relates to narrower siblings like sn_mcp_list_servers or sn_mcp_list_registry.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no exclusions, and no named alternative. An agent must infer from the enumeration that this is a broad one-shot overview rather than a call to make when it only needs one section; nothing states that preference.

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