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 discloses the workflow: it returns a login link when called with no args and accepts a JWT for session login. It also notes that a config-based header is preferred for permanent access. This goes beyond the annotations (idempotentHint=true, readOnlyHint=false) without contradicting them, though it does not detail side effects or session expiration.
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 moderately long but well-structured, with the main flow explained in a few sentences. It front-loads the audience and purpose, then explains the two modes. No unnecessary fluff, though it could be tightened slightly.
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?
For a simple tool with one optional parameter and no output schema, the description covers the essential behaviors: how to trigger the login link and how to pass the token. It does not explicitly describe the response when a token is provided, but the context is mostly complete for agent usage.
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?
The schema provides a bare 'token' property with no description, but the description fully explains its meaning: a JWT to paste for session-only login. It also clarifies that omitting the token returns the login link, adding crucial semantic context that the schema lacks.
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 an IDE agent to the MCP.AI server. It explains the two authentication modes (permanent via config header, session-only via token) and distinguishes from simply connecting. The verb 'authenticate' is specific and the resource is implied.
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?
Explicit guidance is given on when to use the tool: for a permanent connection, the user should add the token to the server config instead of using the tool; for a session-only login, call with the token or with no args to get the browser link. This provides clear 'when to use' and 'when not to use' context.
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 list/get/update/sync operations, and the non-openfinance tools are clearly separate platform utilities. A few pairs could be confused, such as openfinance_list_accounts vs openfinance_get_accounts_detail, or openfinance_get_item_status vs openfinance_list_connections, but the descriptions generally make the intended use clear.
The domain tools follow a consistent openfinance_verb_noun pattern, making the bulk of the API predictable. The deviation comes from the six non-prefixed platform tools, and one or two names like openfinance_provider_status are noun-led rather than verb-led, but overall the convention is coherent.
25 tools is at the heavy end of the range, and the server would feel tighter if some get/list pairs were consolidated. However, the breadth is somewhat justified by the number of Open Finance resource types covered: accounts, transactions, bills, investments, loans, connections, categories, and sync/status operations plus platform utilities.
The Open Finance surface is thorough: connection lifecycle, account data, balances, transactions, credit card bills, investments, loans, categories, sync, and provider health are all covered. There are no significant dead ends, and the additional platform tools handle authentication, marketplace discovery, and system information.