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?
Explains behavioral traits beyond annotations: permanent vs session-based login, the use of Authorization header, JWT token format, and no-arg behavior to retrieve a link. This adds significant value beyond the basic flags (readOnlyHint=false, idempotentHint=true) without contradicting them.
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?
Two sentences, but dense and slightly rambling. Covers all key points without waste, though could benefit from bullet points or clearer separation of the three usage modes. Still efficient for the information conveyed.
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?
Adequate for a simple authentication tool with one parameter. Describes both input modes and the permanent configuration path. Doesn't mention response format, but no output schema is present, and an agent can infer the tool returns a link or confirmation. Missing error handling or timeout details, but not essential for basic use.
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 only defines 'token' as an optional string with no description. The description fills this gap by explaining it expects a JWT pasted by the user, and that omitting it retrieves a login link. Fully compensates for the 0% schema coverage.
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 ties to authentication ('log in', 'access token') and specifies the resource (MCP.AI for IDE agents). It distinguishes from siblings by focusing on authentication, though the phrasing 'MCP.AI for IDE agents...' is slightly indirect and could be crisper.
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 when-to-use guidance through three scenarios (permanent config, session token, no-arg) and practical instructions for each. It doesn't explicitly contrast with alternatives but offers enough context for an agent to know when to call this tool.
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 'marketplace' tool is a sprawling multi-purpose tool covering search, install, subscribe, and more, overlapping with 'authenticate', 'connect', 'toolkit_info', and even 'report_bug'. Tools like 'carf_processo_consultar' have a distinct purpose, but several others (connect, toolkit_info, marketplace) blur boundaries around status/management.
Naming is inconsistent: 'carf_processo_consultar' is a verb_noun in Portuguese, while others are plain English verbs like 'authenticate', 'connect', 'marketplace', 'report_bug'. There is no clear pattern; some are functions, some are nouns, and one mixes domain-specific naming.
The tool count is 7, which is within the recommended rangecase; however, the 'marketplace' tool is overloaded and should likely be split, making the count feel artificial. Still, 7 tools is reasonable for the server's advertised breadth.
For a server named 'CARF: Processo' centered on consulting Brazilian official sources, we only see one domain operation ('carf_processo_consultar'). The rest are platform management utilities unrelated to CARF. There are no obvious lifecycle operations (e.g., list, export, status) for the core domain, making the surface severely incomplete.