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 already declare idempotentHint=true and destructiveHint=false, reducing the burden. The description adds behavioral context by explaining the permanent vs session nature and the no-arg behavior. No side effects or failure modes are described, but the annotation coverage makes this acceptable. No contradiction.
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 structured with a clear main action followed by the permanent and session options. It is slightly verbose but every clause contributes useful information, and the key purpose is front-loaded.
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 simple authentication tool with one optional parameter and no output schema, the description covers both usage modes and the no-arg behavior. It does not detail error cases or the link's destination, but these are not essential for the tool's scope. Overall 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?
The schema has one optional property 'token' with no description. The description fully compensates by explaining that the token is a JWT copied from the browser and that it can be omitted to get a link. This gives the agent essential meaning beyond the schema.
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: it authenticates an IDE agent by logging in via browser and obtaining an access token. The action and resource are specific, but it does not explicitly distinguish from sibling tools like 'connect', so it misses the full 5.
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 instructions with two modes: a recommended permanent configuration via header and a session-only token input. It specifies the call format for both token and no-arg cases, but does not offer explicit exclusions or contrast with 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.
Every tool has a clearly distinct purpose: authenticate for token login, cepim_consultar for CNPJ checks, connect for status, marketplace for discovery/running, report_bug, show_version, and toolkit_info. There is no functional overlap between tools.
Naming is inconsistent: verbs (authenticate, connect), nouns (marketplace), verb_noun (report_bug, show_version), and noun_noun (toolkit_info). The only domain tool, cepim_consultar, reverses the verb_noun pattern, breaking any coherent naming scheme.
Seven tools is moderate, but the server is named 'CEPIM' and only one tool relates to that domain. The other six are generic platform utilities, making the set feel padded and poorly scoped to the intended purpose.
For the CEPIM domain, only a single query operation exists with no additional workflows (e.g., bulk verification, historical checks). While the platform side is thorough, the CEPIM-specific surface is shallow and incomplete for a dedicated service.