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 already indicate idempotentHint=true and destructiveHint=false. The description adds context about token storage (permanent config vs. session-only) and the two auth modes, but doesn't disclose potential side effects, failure modes, or return values. With annotations covering the safety profile, the added transparency is adequate but not rich.
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 a single paragraph of three sentences, covering both modes and configuration in a compact format. It is slightly wordy with parentheticals ('MCP.AI for IDE agents (Cursor, etc.)') but front-loads the login purpose and avoids redundancy.
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 auth tool with one optional param, no output schema, and no nested objects, the description covers the main usage scenarios, the meaning of the token, and the no-arg behavior. It lacks explicit return-value details, but the tool's purpose and invocation are sufficiently described.
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 input schema has 0% description coverage for the sole 'token' parameter. The description compensates by defining it as a 'JWT' pasted from the browser and showing the exact call syntax { token: '<jwt>' }. It does not cover format validation or other constraints, but the core meaning is clear.
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 handles authentication for IDE agents: 'log in in the browser, copy the access token.' It explains the token-based flow and the two usage modes (permanent vs. session), but does not explicitly differentiate it from sibling tools like 'connect'.
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?
Provides specific invocation guidance: call with no args to get the login link, or call with { token: '<jwt>' } after the user pastes a token. It also describes the preferred approach (config header) vs. session-only login, though it doesn't mention alternative tools or when not to use this tool.
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 and action, but several pairs create ambiguity: openfinance_get_item_status vs openfinance_provider_status, openfinance_list_transactions vs openfinance_list_transactions_by_item, and the monolithic marketplace tool overlaps with top-level report_bug and toolkit_info. Descriptions do clarify the differences, but an agent selecting by name alone could easily choose the wrong tool.
The openfinance_* family follows a mostly consistent verb_noun pattern (list_accounts, get_balance, update_transaction_category), which is good. However, top-level tools mix bare verbs, nouns, and verb_noun forms (authenticate, connect, marketplace, show_version, toolkit_info), and openfinance_provider_status breaks the verb-first pattern. The naming is readable but not uniform across the whole set.
25 tools sits right at the heavy boundary, though the server covers two domains: mcp.ai platform management and Open Finance data access. Some tools could be consolidated (list_transactions vs list_transactions_by_item, get_item_status vs provider_status), and marketplace is a monolithic super-tool that bundles many sub-capabilities. Overall the count is defensible but slightly bloated.
The Open Finance surface is thorough: accounts, balances, transactions, credit card bills, loans, investments, connection management, sync, category updates, and provider health are all covered. Minor gaps exist, such as no investment detail beyond the list and connection actions being URL-based rather than first-class tools, but there are no dead ends for typical read/aggregation workflows.