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?
Discloses behavior beyond annotations: explains two invocation modes (with/without token), persistence (permanent vs session). Annotations already indicate idempotency, and description aligns. 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?
Description is informative and front-loaded with purpose. Each sentence adds value. Slightly long but well-structured for a simple tool.
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?
Covers key aspects: purpose, invocation methods, token source. No output schema exists, so missing return value details is acceptable. Lacks error handling notes, but overall complete for a simple auth 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?
Schema coverage is 0%, but description explains the token parameter: a JWT access token. Also explains that omitting it returns a link. Adds full meaning to the only parameter.
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?
Clearly states the tool is for authentication of MCP.AI for IDE agents. Describes two methods: permanent via config or session via token parameter. No explicit differentiation from sibling tools, but the purpose is unambiguous.
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 clear usage guidance: best method (config) and alternative (token parameter). Also mentions calling with no args to get a link. However, no comparison with sibling tools or 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.
Each tool targets a distinct resource or action: the openfinance_* family cleanly separates accounts, transactions, bills, loans, investments, connections, sync, and provider health, while platform tools (authenticate, connect, marketplace, toolkit_info) cover different concerns. Even potentially similar pairs like get_item_status vs provider_status and list_transactions vs list_transactions_by_item are clearly differentiated by their descriptions.
Open Finance tools follow a uniform openfinance_<verb>_<noun> snake_case pattern, and the generic tools are also readable English verbs/nouns (authenticate, connect, report_bug). The main inconsistency is that a few generic tools are bare nouns (marketplace, toolkit_info) while the rest are verbs, but the mix is predictable and never confusing.
25 tools sit at the upper boundary of what is comfortable, and the set spans two distinct domains (Open Finance data access plus MCP platform/marketplace management). Each tool does appear to earn its place, but the count is heavy enough to feel borderline rather than optimally scoped.
The Open Finance surface is thorough: list/get for accounts, transactions, bills, loans, and investments, with sync, connection health, provider status, category correction, and disconnect all covered. The platform side also covers authentication, connection status, marketplace discovery/invocation, bug reporting, and version info, leaving no obvious dead ends for the stated purpose.