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?
Annotations indicate idempotentHint=true and destructiveHint=false. The description adds context about the two login modes and the non-expiring nature of config-based auth. It does not contradict annotations and provides behavioral details beyond them, such as the idempotent nature of calling with or without token.
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 informative but slightly verbose. It front-loads the purpose and then explains both use cases efficiently. Every sentence adds value, though it could be trimmed slightly without loss.
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 no output schema and one optional parameter, the description fully covers the authentication workflow, including permanent vs session options and step-by-step guidance. It is complete enough for an agent to invoke correctly.
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?
With 0% schema description coverage, the description compensates fully by explaining that the optional 'token' parameter is a JWT for session login, and that omitting it returns a login link. This adds crucial semantic meaning missing from 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 that the tool is for authentication, explaining two modes: browser login with token paste or config-based permanent login. This distinguishes it from sibling tools like 'connect' and provides specific verb-resource mapping.
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 gives explicit guidance on when to use it: for logging in, with options to either paste a token for session-only login or add it to config for permanent access. It also implies the alternative of config-based login for permanent connections, which helps the agent choose correctly.
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 have clearly distinct purposes (e.g., force_sync vs get_item_status, list_accounts vs get_accounts_detail). Minor overlap exists between list_transactions and list_transactions_by_item, and between get_account_balance and list_accounts (which also contains balance), but descriptions clarify when each should be used.
All openfinance_* tools follow a consistent snake_case verb_noun pattern (list, get, force_sync, disconnect, update). The generic tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) are also lowercase with underscores where needed, though they lack the openfinance prefix. No mixing of camelCase or chaotic patterns, so mostly consistent with minor deviation.
25 tools is on the heavy side for a single server, but justified given the breadth of Open Finance operations (accounts, transactions, bills, loans, investments, connections, categories, provider status). The count is borderline heavy but not excessive for the domain, though some consolidation could be possible (e.g., merging get_account_balance into list_accounts).
The tool surface covers the full lifecycle for financial data: listing, getting details, forcing syncs, disconnecting, updating categories, checking provider status, and handling investments/loans/bills. No obvious dead ends; even connection management includes search, connect URLs, and re-authentication flows. The set appears comprehensive for its intended purpose.