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?
Goes beyond the annotations (readOnly=false, idempotent=true) by explaining the flow: it returns a link when called with no args, and accepts a JWT token for session login. It also mentions the permanent option via config, which is not in annotations. No contradictions.
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 paragraph but is informative. It could be more structured (e.g., bullet points) but is not overly long. It front-loads the purpose and then gives usage details. Slightly rambling but still concise enough.
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 covers the main usage modes and gives context on how to authenticate (browser, token). It doesn't mention what the response looks like, but for an authentication tool that sets a token, the reader likely knows it returns success/failure. Provided there is no output schema, the description is reasonably 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?
Since the schema has no description for the 'token' parameter and coverage is 0%, the description fully compensates by explaining that `token` is the JWT to authenticate, and how to use it. No other parameters exist, so the single parameter is well-explained.
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 authenticates by logging in via browser and obtaining an access token From the context, it distinguishes itself from sibling tools like 'connect' and 'toolkit_info' by being specifically about authentication and token management.
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 explicit when-to-use guidance: explains the permanent config approach vs session-only token paste, and gives exact call patterns (with/without token). It clearly instructs the agent on how to invoke the tool in different scenarios, making it obvious when to use this tool versus alternatives.
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 serves a distinct purpose: authenticate handles login, connect reports status, marketplace is the central hub for searching and executing MCPs, report_bug sends feedback, show_version displays versions, sintegra_ms_consultar performs a specific data lookup, and toolkit_info summarizes the environment. The only potential overlap is between authenticate and connect, but they are clearly separated by actions (login vs. check status). The marketplace tool is broad but has a well-defined scope, so misselection is unlikely.
Naming is mixed: some tools use verb_noun (show_version, toolkit_info), some are single verbs (authenticate, connect), and marketplace is a noun. Additionally, sintegra_ms_consultar includes a proper name and a Portuguese verb, deviating from the pattern. While all names are readable, the inconsistency is noticeable and could confuse agents expecting a uniform convention.
Seven tools is a reasonable count for a platform that combines a marketplace, user management, and a specific data query. The count is not excessive and each tool seems necessary, though the marketplace tool bundles many sub-actions (search, describe, invoke, list, install, subscribe, etc.) into one surface, which might justify a higher count but still remains within a sensible range.
The platform covers core operations: authentication, connection status, marketplace discovery/execution, bug reporting, version info, and toolkit state. Minor gaps exist, such as a dedicated logout or token revocation function, but the marketplace tool includes billing and subscription management, so most needs are met. The SINTEGRA MS tool is a standalone query, which is complete for its purpose.