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?
Adds meaningful context beyond the annotations: explains that adding to config creates a permanent non-expiring connection, while pasting a token is session-only. Also clarifies that calling with no args yields a login link. This complements the idempotentHint and readOnlyHint annotations without contradiction.
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 packs useful instructions into a few sentences, front-loading the core purpose. It is somewhat dense and run-on, but every part contributes necessary information, so it remains reasonably concise.
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?
Covers the two main usage modes well, but does not describe the response format, potential errors, or what the agent should expect after calling. With no output schema, this missing return-value information leaves an important gap for the agent to handle the auth flow confidently.
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 lists 'token' as a string with no description (schema coverage 0%). The description fully compensates by explaining that the token is a JWT pasted by the user for session login, and that omitting it retrieves a login link, thus giving complete semantic meaning.
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 clearly specifies the tool's purpose: authenticating to MCP.AI for IDE agents via browser login and token exchange. It enumerates two distinct usage modes (permanent config header vs session token), making it distinguishable from potential sibling tools like 'connect'.
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?
Provides clear instructions for both permanent configuration and session-only login, including when to pass a token and when to call with no args to get a link. However, it does not explicitly compare to alternative tools or state when not to use authentication, so it falls 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.
Most tools have distinct purposes, but authenticate and connect both deal with connection/auth, and marketplace overlaps with toolkit_info in describing the toolkit state. The descriptions are detailed enough to disambiguate in most cases.
Naming is inconsistent: some tools are single verbs (authenticate, connect), some are verb_noun (report_bug, show_version), one is a noun (marketplace), one is a compound (toolkit_info), and the domain tool follows a different pattern (sancoes_australia_consultar). No consistent convention.
With 7 tools, the count is within a reasonable range. However, the server is ostensibly about Australian sanctions, yet only one tool is domain-specific; the rest are platform utilities, making the overall scope feel a bit unfocused but not excessive.
The only domain-specific tool is a single lookup for sanctions. There is no batch query, history, or other sanctions-related operations, but for a simple compliance check, it may suffice. The platform tools cover connection and lifecycle needs, so no obvious dead ends.