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?
The description reveals behavior beyond annotations: two modes (permanent via config, session via token param) and the no-args behavior of returning a link. Annotations already note idempotence and non-destructiveness. It doesn't describe potential errors or return value details, but for an auth tool it's adequate.
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 compact but packs a lot of information. It's two sentences, but the second is long and contains multiple clauses. All content is relevant and earns its place, though a bulleted structure could improve readability.
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 param, no output schema), the description covers the necessary behavioral details: how to authenticate permanently and temporarily, and what happens with no args. It doesn't explicitly state the return format, but that's implied ('get the link'). Complete enough for an AI agent to invoke correctly.
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 a single 'token' string with no description (0% coverage). The description compensates fully by explaining the token as a JWT and the no-arg case for getting the link. It gives clear semantics for when to include or omit the parameter.
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 defines the tool's purpose: authenticating IDE agents via browser login and token capture. It describes the specific resource (access token) and the flow. However, it doesn't explicitly contrast with sibling tools like 'connect', so it slightly misses explicit differentiation.
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: adding token to config for permanent connection, or passing token for session-only login, or calling with no args to obtain the link. It tells the agent exactly when to use which invocation, which exceeds basic guidance. It doesn't mention alternative tools, but the instructions are highly actionable.
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 core query tool and platform utilities are distinct, but connect and toolkit_info both report connection status and could confuse an agent. The marketplace tool is multi-functional but clearly scoped. Overall, purposes are mostly separable.
Names mix English and Portuguese (authenticate vs. beneficiario_final_consultar) and use inconsistent patterns: verb (connect, authenticate), noun (marketplace), noun_noun (toolkit_info), and verb_noun (report_bug, show_version). The Portuguese tool reverses the typical verb_noun order.
Seven tools is within a reasonable range, but most are generic platform utilities unrelated to the server's stated purpose of beneficiary final queries. The core domain is served by a single tool, while the rest feel bolted on.
For the beneficiary final domain, the single query tool covers the basic use case, but there are no supporting operations like batch queries, history, or credit management. The platform tools are general but don't address domain-specific needs, leaving the surface incomplete for a dedicated compliance service.