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 discloses the behavior beyond annotations: it explains that calling with no args returns a link, and that providing a token sets up session authentication. It also mentions the permanent vs. session distinction, aligning with the idempotentHint annotation.
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 moderately sized but well-structured, breaking down the usage into two clear paths. It is front-loaded with the main purpose and then elaborates on methods, avoiding unnecessary verbosity.
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?
The description is complete for the tool's complexity: it explains both authentication workflows, the role of the token, and the outcome of each call. It does not need to describe return values since no output schema is provided.
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?
Although the schema only lists 'token' without description, the description clarifies that token is a JWT and explains that it is optional (no args for link). It also details the two usage modes, adding meaningful context.
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 the user for IDE agents via a browser login and token, distinguishing it from sibling tools like connect or marketplace. It explains the two authentication methods explicitly.
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 provides clear instructions on how to use the tool, including two approaches: permanent config via header and session-only via token. It also notes that calling with no arguments returns a login link, which guides the user on when to use it.
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.
Each tool has a clearly distinct purpose: authentication, connectivity status, marketplace search/execution, bug reporting, version info, toolkit state, and the dental council query. No two tools overlap or could be confused.
Naming is highly inconsistent: some tools use verbs (authenticate, connect, report_bug), some use nouns (marketplace, toolkit_info), one uses camelCase (cro_pr_cadastro_consultar), and show_version mixes verb+noun. There is no discernible pattern or convention across the set.
Though 7 is within a normal range, only one tool (cro_pr_cadastro_consultar) relates to the server's stated domain. The other six are generic platform utilities (authenticate, marketplace, etc.) that bloat the set and make the server feel unfocused and over-tooled for its apparent purpose.
The single domain tool appears to handle the core consultation need, but a richer set (e.g., separate lookups by registration number, name, or status) could improve coverage. The generic utilities cover platform needs, but the domain surface is minimal and only supports one kind of query.