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 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotentHint=true, which aligns with the description's indication of non-expiring connection. The description adds behavioral context about permanent vs session login and token handling.
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?
Three concise sentences, front-loaded with purpose. Each sentence adds value without 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?
Covers the key authentication scenarios and token management. No output schema specified, but the description implies the expected return (link or success). Could mention return format explicitly.
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?
Schema has 0% description coverage for the single optional token parameter, but the description fully explains its purpose (a JWT token) and the two calling modes (with or without token). This compensates completely.
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 that the tool handles authentication for MCP.AI IDE agents. It distinguishes from siblings like connect and openfinance tools by focusing on the 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?
Explicitly describes three usage scenarios: adding token to config for permanent login, passing token as argument for session-only, or calling with no arguments to get a login link. Provides clear guidance on when to use each.
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 targets a distinct resource or action (e.g., accounts, transactions, loans, investments, credit card bills, connection status, provider status, sync, marketplace, authentication). Descriptions are highly detailed, making overlaps virtually nonexistent. The only potential overlap (openfinance_list_transactions vs. openfinance_list_transactions_by_item) is resolved by the latter being a consolidated analysis tool for a whole connection.
All tools follow a consistent snake_case pattern. Open Finance tools are uniformly prefixed with 'openfinance_' and follow a clear verb_noun structure (e.g., openfinance_list_accounts, openfinance_get_account_balance). Non-Open-Finance tools (authenticate, connect, marketplace, etc.) also use simple, predictable verb names. No mix of conventions.
With 25 tools, the count is on the higher side but justified by the comprehensive scope covering Open Finance banking data, marketplace, and utility functions. The domain requires many endpoints (accounts, transactions, loans, investments, credit card bills, sync, etc.). A slight redundancy exists (e.g., two transaction listing tools), but they serve distinct use cases. The count is well-scoped for the complexity.
The tool set provides excellent read coverage for accounts, transactions, loans, investments, and credit cards, plus write support for category updates and sync forcing. Missing are tools for directly creating or deleting connections (though search provides connect_url and disconnect exists) and for managing MCPs beyond the marketplace. No critical gaps that would cause agent failures, as the core data retrieval and category correction are covered. Minor gaps exist in write operations and connection lifecycle management.