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?
The description adds behavioral context beyond annotations by explaining the two different outcomes (link vs. token acceptance) and the session/permanent distinction. It does not contradict the idempotentHint and destructiveHint annotations.
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 and well-structured, starting with the principal action and then outlining two use cases. It is slightly dense but not overly verbose, earning a score just below the highest tier.
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 simple tool with one optional parameter and no output schema, the description covers most needed context: token origin, usage modes, and the config alternative. It could be more explicit about the return format when no args are provided, but overall it is sufficient.
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 that 'token' should be a JWT from browser login, and that omitting it returns a link. This gives complete semantic 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 states the tool's purpose: authenticate MCP.AI for IDE agents by providing an access token or obtaining a login link. It distinguishes from sibling tools by focusing solely on authentication.
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 two modes: using a config for permanent access or pasting a token for session-only login. It also tells the user to call with no args to get the link. However, it does not explicitly contrast with sibling tools 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.
The openfinance_ tools are mostly distinct by resource/action, but there are several overlapping pairs: list_accounts vs get_accounts_detail, list_credit_card_bills vs get_credit_card_bill, list_transactions vs list_transactions_by_item, and connect vs toolkit_info vs openfinance_list_connections. The descriptions help disambiguate, but an agent could still misselect between these related tools.
The core banking tools consistently follow an openfinance_<verb>_<noun> pattern, which is a strong and readable convention. The generic platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) break that pattern and use mixed naming styles, creating two distinct naming tiers within the same server.
25 tools sits at the upper borderline of what feels reasonable for one server. The Open Finance domain justifies many read/query tools, but the inclusion of platform meta-tools like marketplace, connect, toolkit_info, report_bug, and show_version inflates the count beyond a tightly focused bank-data scope.
The Open Finance surface is largely complete: connectors, sync, disconnect, accounts, balances, transactions, categorization, credit card bills, loans, investments, and provider status are all covered. Minor gaps exist, such as the lack of a dedicated investment detail endpoint and limited consent/permission introspection, but agents can work around these with the existing tools.