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?
Beyond annotations, the description reveals that no-args returns a login link, the token is a JWT, and the config header gives a non-expiring connection while pasting provides session-only access. This adds meaningful behavioral context, though failure modes and config-overwrite behavior are not covered.
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?
Three sentences carry useful information, but the first sentence is cluttered with 'MCP.AI for IDE agents (Cursor, etc.)' and the instruction tone is conversational. It could be more streamlined while remaining front-loaded with the core purpose.
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-parameter auth tool with no output schema, the description covers the essential flows: permanent config, session-only paste, and no-args link retrieval. It adequately explains the token type and usage. A brief note on post-login response or errors would improve completeness.
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 input schema only defines a string token with no description. The description compensates by explaining the JWT format and the effect of providing the token vs omitting it. It makes the parameter's usage clear, though it does not detail validation or error handling.
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 tool as authentication for MCP.AI IDE agents, involving browser login and token provisioning. It distinguishes from siblings like connect or show_version by focusing on token-based auth. The purpose is embedded in usage instructions rather than a crisp standalone statement.
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 usage context: two modes (permanent config vs session-only) and when to call with or without the token argument. It recommends the config approach but does not explicitly contrast with alternative tools or state when not to use 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.
Most tools are clearly distinct: authenticate handles login, connect shows status, marketplace discovers and runs tools, report_bug is for feedback, show_version is for versions, toolkit_info shows installed state, and the TSE tool is a specific query. However, connect and toolkit_info both touch on connection status, which could cause minor confusion.
Names follow no single pattern: some are single-word verbs (authenticate, connect), some are verb_noun snake_case (report_bug, show_version), one is a noun_noun (toolkit_info), and the TSE tool is a long snake_case phrase (tse_quitacao_eleitoral_consultar). This mix makes the set feel inconsistent and unpredictable.
Seven tools is a reasonable count, but the set is split between general MCP platform management and a single TSE-specific consultation. This split makes the server feel unfocused and broader than its stated purpose, though it is not extreme.
The TSE domain is severely underrepresented, with only one consultation tool and no associated operations like validation or history. The platform management tools are fairly complete but belong to a different domain, leaving the actual stated purpose with significant gaps.