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 indicate idempotentHint=true and destructiveHint=false. The description reveals that the token is non-expiring if added to config, and that session-only login is temporary. It also mentions the browser interaction requirement. It does not contradict annotations. It doesn't cover potential pitfalls like invalid token handling, but given annotations, it adds reasonable context.
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 one long sentence but packed with useful info. It is front-loaded with target audience and action. It's a bit verbose in the middle, but every part serves a purpose. It could be split into clearer sentences, but it's appropriately sized for the complexity.
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 that there is no output schema, the description explains what the user will experience: they get a link to log in, or they can paste a token. The tool has one optional param, and the description covers all modes (config, token, no-args). It even addresses the target environment (IDE agents). For a simple auth tool, this is fairly complete.
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 has one optional parameter 'token' with no description. The description explains that 'token' should be a JWT pasted by the user for session-only login, and that no args gets the link. This adds meaning beyond the schema, partially compensating for 0% schema coverage. However, it doesn't specify the token format or what happens when an invalid token is provided, so full semantics are not covered.
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: to authenticate an IDE agent with the server by either obtaining a login link or accepting an access token. It distinguishes itself from siblings by focusing on login/authentication, unlike connect or marketplace. However, it mixes configuration guidance with tool invocation, making it slightly less crisp.
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 usage scenarios: best practice is to add token to config for permanent connection, or paste token for session-only login, or call with no args to get link. It clearly explains when to use each mode and even mentions adding to server config as an alternative, which helps the agent decide when to invoke vs. configure.
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.
A maioria das ferramentas tem papéis distintos e reconhecíveis, mas a ferramenta 'marketplace' é um canivete suíço que abrange busca, descrição, invocação, instalação e biblioteca de prompts, misturando responsabilidades de contas, faturamento e descoberta de MCPs. Há também sobreposição entre 'connect' e 'toolkit_info' (ambos informam status de conexão e provedores). As descrições ajudam a diferenciar, mas a ambiguidade é real.
Todas as ferramentas seguem razoavelmente snake_case minúsculo, mas o padrão varia entre verbo solto (authenticate, connect), verbo_substantivo (report_bug, show_version) e substantivos isolados (marketplace, toolkit_info). A mistura de idiomas (inglês na plataforma e português na ferramenta mpt_sp_cnf_consultar) é compreensível, mas quebra a previsibilidade do padrão.
Com 7 ferramentas, o conjunto está dentro de uma faixa saudável e cada ferramenta contribui para o fluxo geral da plataforma. Não há excesso nem escassez extrema de ferramentas.
O fluxo principal de consultar uma certidão — autenticar, conectar, realizar consulta e processar cobrança — é coberto, assim como ações de suporte (reportar bug, ver versão). Porém, o servidor acaba delegando demais funcionalidades à ferramenta marketplace (buscar, descrever, invocar, assinar, cancelar), e ferramentas como histórico de faturamento ou gestão de assinaturas não possuem superfície própria, embora a cobertura essencial para o propósito declarado exista.