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 include idempotentHint=true and destructiveHint=false. The description adds flow details (token handling, link generation) but does not elaborate on side effects like setting authentication state or error behavior.
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 three sentences, front-loaded with the key purpose, and each sentence adds essential information without redundancy. No wasted words.
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?
While the description covers the authentication flow well, it lacks details on return values (e.g., what the tool returns beyond 'the link') and error handling. Given no output schema, this is a notable gap.
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 fully compensates by explaining the 'token' parameter: it is a JWT, optional, and its presence determines behavior (session login) or absence (return link).
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 for MCP.AI IDE agents, with specific steps for login and token handling. It distinguishes from siblings like 'connect' by detailing the token-based authentication flow.
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 specifies when to use the tool (for IDE agents) and provides two methods (permanent config or session token). However, it does not explicitly mention when not to use it or compare with alternatives like 'connect'.
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 map clearly to a distinct openfinance resource or action (accounts, transactions, bills, investments, loans, connections, provider health), and the platform utilities are a separate family. The only realistically confusable pairs are openfinance_list_transactions vs openfinance_list_transactions_by_item and openfinance_list_accounts vs openfinance_get_accounts_detail, but the descriptions draw sharp boundaries between them.
The 19 openfinance_* tools follow a strong openfinance_<verb>_<noun> convention, with only minor exceptions like openfinance_provider_status and openfinance_list_transactions_by_item. The six platform tools mix bare verbs (authenticate, connect), nouns (marketplace, toolkit_info), and verb_noun (report_bug, show_version), but they are clearly a separate utility layer.
25 tools sits at the top of the 'feels heavy' band. The number is defensible for a full Open Finance data product plus platform management tools, but an agent is exposed to a lot of surface area, and the same server mixes a banking-data adapter with a marketplace/utility layer.
The openfinance surface covers the full lifecycle: search/connect/reconnect/disconnect banks, force-sync, item status, provider incidents, accounts, balances, transactions per account and per connection, credit-card bills with paid-status derivation, investments and investment transactions, loans, loan detail, and transaction categorization. Platform tools cover auth, connection status, toolkit state, version, bug reporting, and marketplace operations, so there are no obvious dead ends.