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 readOnlyHint: false. The description adds behavioral context by explaining that calling with no args returns a link (non-destructive) and that adding token to config makes it permanent. It does not contradict annotations and provides useful insight into state changes.
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 long, front-loading the purpose, and every sentence adds value without unnecessary words. It is well-structured for quick comprehension.
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 authentication tool with one parameter and no output schema, the description covers all needed information: the two usage patterns, permanent vs session, and the effect of parameter. It is complete 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?
Despite 0% schema coverage, the description fully explains the single optional parameter 'token': it should be a JWT for session login, or omitted to get the auth link. This provides complete semantic meaning beyond 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 the tool is for authentication, detailing methods to log in and obtain an access token. It uses specific verbs like 'log in' and 'authenticate', and distinguishes itself from siblings by being the primary authentication tool.
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 usage scenarios: adding token to config for permanent connection, passing token for session login, or calling with no args to get a link. However, it does not explicitly exclude alternatives or mention when not to use it, missing some comparative guidance.
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.
Each tool has a clearly distinct purpose. Even overlapping-looking tools like list_transactions vs list_transactions_by_item are clearly differentiated (per-account vs consolidated per-connection), and get vs list variants follow standard conventions. The marketplace tool bundles multiple actions but is its own meta-tool. No two tools appear to do the same thing.
The openfinance_ prefix provides a consistent pattern for banking operations, with clear get/list/update/force_sync verbs. A few non-prefixed meta tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) break the pattern, but they represent different functional domains and are still readable. Overall the convention is predictable.
At 25 tools, this is on the heavy side per the calibration guidelines (16-25 feels heavy). However, the breadth of Open Finance resources (accounts, transactions, investments, loans, credit cards, connections, plus meta operations) largely justifies the count. It's borderline and could benefit from consolidation, but it's not excessive.
The tool surface covers the domain comprehensively: listing and getting accounts, transactions, investments, loans, credit card bills, connections, status, sync, category management, and provider health. Missing operations are minor (e.g., no explicit 'get single transaction' but list covers it; no create/update on banking data besides category and disconnect). Core workflows are fully supported.