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 declare idempotentHint=true and destructiveHint=false, which the description does not contradict. The description adds behavioral context: calling with no args returns a login link (browser interaction), and passing a token performs a session login. It does not detail what happens after login (e.g., session persistence), but given the idempotent nature and non-destructive flag, the description provides sufficient extra value beyond annotations.
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 a single, dense paragraph that front-loads the tool's purpose and immediately gives actionable instructions. Every sentence adds value: explaining the browser flow, proposing the best permanent setup, and offering the session-only alternative. No fluff or repetition.
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?
Given the tool's simplicity (one optional parameter, no output schema) and the clear guidance in the description, the description is complete. It covers the two usage modes, explains the permanent vs. session options, and even mentions the header format. The lack of an output schema is acceptable because the tool's result is a connection state, not a data resource.
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 schema has one optional parameter 'token' with no description coverage (0%). The description explains its semantics: it's a JWT to be pasted for session-only login. It also clarifies that calling without the parameter triggers a link generation. This fully compensates for the lack of schema description, though it doesn't detail token format beyond 'jwt'.
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 states the tool's purpose: authenticate an MCP IDE agent by logging in via browser and providing a token. It distinguishes itself from sibling tools (connect, marketplace, etc.) by focusing on authentication, not connectivity or browsing. The verb 'authenticate' plus the token parameter make the resource and action explicit.
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?
The description provides explicit when-to-use and how-to-use guidance: for permanent connections, add token to server config; for session-only, pass token or call with no args to get a link. It explains the trade-offs between permanent and session-based login, which helps the agent decide which path to recommend.
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 tools are mostly distinct: authenticate, connect, marketplace, mpt_pr_cnf_consultar, report_bug, show_version, and toolkit_info each have clear purposes. The only minor overlap is between authenticate and connect, but their descriptions differentiate login flow from status checking. The marketplace tool is broad but well-delineated as a single capability.
Naming is inconsistent: some tools use single verbs (authenticate, connect), some use nouns (marketplace, toolkit_info), and one uses a non-standard underscore mix (mpt_pr_cnf_consultar). There is no clear verb_noun pattern or stylistic uniformity, making it harder to predict tool names.
While 7 tools is within a reasonable range, only one (mpt_pr_cnf_consultar) actually pertains to the server's stated domain of Brazilian certificates. The other six are generic platform utilities that would be better placed in a separate platform server, leaving the server grossly mismatched to its purpose.
The server fails to cover the domain adequately: it offers only a single query tool (mpt_pr_cnf_consultar) with no additional lifecycle operations (e.g., certificate history, validation, or status checks). The generic platform tools do not fill this gap, leaving the actual certificate workflow threadbare and likely to cause agent dead-ends.