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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds context beyond annotations: explains that authentication can be permanent or session-based, that token can be provided to set session, or omitted to get a link. Consistent with idempotentHint (calling with same token idempotent), 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 moderately concise, front-loaded with purpose. Every sentence adds value (purpose, methods, best practice). Could be slightly tighter but overall efficient.
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 scenarios: permanent vs. session, how to obtain token, how to use. Lacks details on return values or error handling, but sufficient for typical authentication flow without output 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 has 0% coverage for the one parameter 'token'. The description compensates fully: explains that token is optional, what it represents (JWT access token), and behaviors for providing it vs. not. Adds essential meaning.
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 specifies the tool's role: authenticating to MCP.AI for IDE agents. It details two methods (config-based permanent token or session-only via paste) and distinguishes the resource (access token, login) effectively.
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 explicit usage guidance: when to use config vs. paste, step-by-step instructions (log in, copy token, paste), and best practices. Does not explicitly exclude siblings but the guidance 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.
Tools are largely distinct: openfinance_* tools cover specific resources (accounts, transactions, bills, loans, investments) with clear boundaries. Some overlap exists between list_transactions and list_transactions_by_item, and between status/sync tools (get_item_status, force_sync, provider_status), but descriptions are detailed enough to guide selection.
The openfinance_* prefix provides strong consistency for the bulk of tools, with clear verb_noun patterns (list, get, update, force_sync). The platform tools (authenticate, connect, marketplace, report_bug, etc.) break the pattern but are few and their names are intuitive. Overall, minor mixing of conventions but readable.
25 tools is on the higher side but appropriate for a comprehensive Open Finance and platform management server. The count includes both data access (accounts, transactions, bills, loans, investments) and platform utilities (authentication, connection state, marketplace). No redundant tools; each serves a clear purpose.
The surface covers the core read operations for connected banks (accounts, transactions, bills, loans, investments), connection management (sync, status, disconnect), and category correction. Minor gaps include no get-transaction-by-id and no update for account metadata, but these are not critical for the typical use case of a banking data aggregator.