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 declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false. The description adds behavioral value beyond these: it discloses the permanent non-expiring vs session-only distinction, what happens with no args (returns a link), and the token-as-JWT expectation. No contradiction exists between the description and annotations.
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?
All content is informative, but the description is a dense, run-on paragraph mixing config setup advice, security details, and invocation modes without structural breaks. It opens with context ('MCP.AI for IDE agents') rather than the core action, and would benefit from clearer partitioning of the config path versus the paste-token path.
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?
For a single-optional-parameter auth tool with no output schema, the description covers the essential flow comprehensively: browser login, token retrieval, two successful login paths (config-based permanent, session-based), and the no-arg link mode. The moderate complexity is adequately addressed given the sparse annotations and schema.
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?
Schema coverage is 0%, so the description carries the full burden for the 'token' parameter. It compensates well by specifying the JWT format and clarifying that passing the token yields session-only login, while also documenting the no-arg alternative. This adds meaning the bare schema (a plain string property) does not convey.
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 identifies the verb (authenticate) and resource (MCP.AI for IDE agents), explaining the browser-login/copy-token flow. It is specific enough to distinguish the tool's intent, though it reads more like agent instructions than a crisp purpose statement, and it doesn't explicitly differentiate from the sibling 'connect' tool.
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 clear internal usage branches: calling with no args yields the auth link, calling with a token performs session-only login, and it recommends adding a header to config for a permanent non-expiring connection. This gives strong context on how and when to invoke each mode, though it offers no explicit exclusion guidance or contrast with sibling tools like 'connect'.
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 mega-tool containing search, describe, invoke, install, subscribe, prompt-library, and even bug-reporting actions, which overlaps with the separate report_bug tool. connect and toolkit_info also overlap in connection/status reporting, making tool selection ambiguous.
Names mix verb-style actions (authenticate, connect, report_bug), noun-style labels (marketplace, toolkit_info), and an inconsistent Portuguese snake_case domain tool (sintegra_ma_consultar). There is no clear or predictable naming convention across the set.
Seven tools is a reasonable count, but it is misleading because marketplace alone bundles well over ten distinct capabilities under one name. The surface would be more coherent and better counted if those actions were split out.
The server covers authentication, connection status, marketplace discovery/execution/install, bug reporting, version info, and toolkit state. However, management operations like uninstall/subscription handling are hidden inside marketplace, and the SINTEGRA MA domain is reduced to a single query with no related history or supporting tools.