Skip to main content
Glama
Sign In

ModelsLab Agent Control Plane

by io.github.ModelsLab
OverviewDiscussionsAdmin

Agent Token Management

agent-tokens
Manage Sanctum access tokens for the authenticated user.
Actions: list (view all tokens), revoke (revoke a specific token by ID),
revoke-others (revoke all tokens except current), switch-account (get a token for a team account).
All actions require authentication.

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": {
      "action": "<action>"
    },
    "name": "agent-tokens"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesThe token action: list, revoke, revoke-others, switch-account
token_idNoToken ID to revoke (required for revoke action)
device_nameNoDevice name for new token (optional for switch-account)
token_expiryNoToken expiry: 1_week, 1_month, 3_months, never (optional for switch-account)
account_usernameNoUsername of the team account to switch to (required for switch-account)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations only declare openWorldHint=true, leaving the destructive/read-only profile entirely to the description. The description adds real behavioral context ('All actions require authentication') and distinguishes destructive actions (revoke, revoke-others) from the read-only 'list', but never states that revocation is immediate/irreversible or what happens to the current session. Mixed read/write tool with no destructiveHint means more disclosure was expected.

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?

Compact and front-loaded: the resource is named first, then the four actions are listed in a scannable form, then the auth prerequisite. Minor inefficiency from the leading indentation and line-break formatting, but no wasted sentences.

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?

There is no output schema, so the description is not expected to explain returns, and 100% schema coverage handles parameters. However, for a multi-action tool that mixes a read-only list with irreversible-looking revocations and zero destructive annotations, the description leaves the agent without consequence or post-condition information.

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%, so the schema already documents action, token_id, device_name, token_expiry, and account_username with per-action requirements. The description's action parentheticals roughly mirror that mapping and add no new parameter meaning (e.g., expiry format nuances or device_name semantics). Baseline 3 is appropriate.

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?

States a specific verb+resource (manage Sanctum access tokens) and enumerates all four actions with parenthetical clarification, so an agent knows exactly what the tool does. It does not, however, differentiate itself from the closest sibling agent-api-keys, which is a plausible source of confusion.

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?

The action enumeration implies when each mode applies, and 'All actions require authentication' sets a prerequisite. But there is no guidance on choosing between revoke vs revoke-others vs switch-account, and no when-not-to-use or alternative-tool routing against agent-api-keys or agent-auth.

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

All ModelsLab Agent Control Plane 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