MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide idempotentHint=true and destructiveHint=false, and the description adds meaningful context beyond that: token config gives a permanent non-expiring connection, pasting a token gives session-only login, and calling with no args returns a login link. It does not describe errors or side effects, but it covers the important behavioral distinctions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the tool's purpose and uses three sentences to cover two authentication paths plus the no-args behavior. It is slightly dense and mixes configuration advice with invocation guidance, but every clause contributes information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter auth tool with no output schema, the description covers the core workflows: browser login link, session token, and permanent header configuration. It does not mention response formats, error handling, or security warnings, but the essential selection and invocation information is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema only shows a bare 'token' string with 0% description coverage. The description fully explains the parameter: it is an optional JWT for session login, and omitting it returns the login link. This completely compensates for the schema's lack of detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly identifies the tool as authentication for MCP.AI IDE agents, using clear verbs like 'log in' and 'authenticate'. It distinguishes itself from sibling tools by scoping to the MCP.AI login flow and specifying two concrete authentication modes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear context for when to use the tool (to authenticate MCP.AI for IDE agents) and provides explicit guidance for permanent vs session-only authentication. It does not explicitly name alternative tools or state when not to use it, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The three openai_billing_* tools are clearly distinct, and the platform utilities (authenticate, connect, toolkit_info, show_version) mostly have separate roles. However, the marketplace tool is a sprawling mega-tool that overlaps with connect (auth URLs), toolkit_info (installation state), and even report_bug, making the boundaries fuzzy and increasing the chance of misselection.
Naming is mixed: some tools use a consistent openai_billing_ prefix with verb_noun structure, while others are bare verbs like authenticate and connect, or a bare noun like marketplace. There is no uniform pattern across the set, which makes it harder to predict tool names.
Nine tools is a reasonable count, but the marketplace tool packs in many sub-operations (search, describe, invoke, install, subscribe, prompts), so the effective surface is much larger than the count suggests. Still, the visible count is not excessive and each platform utility earns its place.
For the stated OpenAI Billing domain, the set covers account listing, cost reports, and usage reports, giving solid read-only coverage. Missing operations like invoice/payment details or account disconnection are minor gaps, and the platform tools add broader lifecycle coverage for connections and the marketplace.