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 indicate idempotentHint=true and destructiveHint=false, which the description aligns with (no destructive actions). The description adds behavioral context: it explains the authentication flow (browser login, token copy), the two modes, and the permanence of the config-based approach. It does not contradict annotations. It could mention that the token is sensitive, but that's minor.
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 contains multiple pieces of information: the target audience, the login process, the two modes, and the call patterns. It is somewhat dense but not overly long. It could be structured with bullet points for clarity, but it is still concise and front-loaded with the main 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?
Given the tool's simplicity (one optional parameter, no output schema), the description covers the essential usage scenarios and provides enough context for an agent to invoke it correctly. It explains the two modes and the argument behavior. It could mention what the response looks like (e.g., success message), but that is not critical. The description is complete enough for this tool.
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 parameter 'token' with no description. The description explains that the token is a JWT to be pasted for session-only login, and that calling with no args returns the link. This adds meaning beyond the schema, but the description does not fully elaborate on token format or validation. Since schema coverage is 0%, the description compensates partially, but the parameter semantics are still somewhat thin.
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: to authenticate an IDE agent by logging in via browser and obtaining an access token. It distinguishes between two modes (permanent config-based and session-only token paste), which adds specificity beyond the name 'authenticate'.
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 explicit guidance on when to use this tool: for logging in and obtaining a token. It also explains the two usage scenarios (permanent via config header, session-only via token argument) and even instructs to call with no args to get the link. This is clear and actionable.
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 pncp_* tools are mostly differentiated by data type, but there is real overlap: pncp_buscar, pncp_listar, and pncp_oportunidades all search licitações, while pncp_detalhe and pncp_processo both return full details and pncp_resultado overlaps with pncp_detalhe(resultado=true). Detailed descriptions help, but an agent could easily pick the wrong search or detail tool.
Naming is inconsistent: English platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) sit alongside Portuguese pncp_* names, with some verbs (buscar, listar) and mostly nouns (atas, contratos, detalhe, processo, texto). There is no single predictable verb_noun or resource_action convention.
19 tools is in the heavy range and includes 6 generic platform/account tools that are unrelated to the PNCP procurement domain. The 13 pncp_* tools are defensible for a broad read-only procurement API, but several overlap enough that the count feels slightly bloated rather than tightly scoped.
The PNCP side covers the core read-only procurement lifecycle well: keyword search, value-ranked listing, opportunities, full detail, edital text, document downloads, winners, contracts, atas, historical data, PCA, and buyer organs. Minor gaps exist, such as losing bids/lances being explicitly unavailable and the marketplace features being bundled into one overloaded tool instead of separate ones.