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 already indicate idempotentHint=true and non-destructive. Description adds that calling with no args returns a login link, while token arg logs in. No contradictions.
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?
Four sentences conveying necessary info; could be slightly more concise but no extraneous details.
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 both usage modes (permanent config and session token) and correctly describes behavior. No output schema needed; return values are implied (success or link). Complete for its purpose.
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 coverage is 0%, but description partially compensates by stating token is a JWT string. However, it does not detail constraints (e.g., format, length) or that it's optional.
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 identifies the tool's purpose: handling authentication via access token or login link. It distinguishes from siblings which are unrelated (e.g., connect, marketplace).
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 clear context: best to add token to config for permanent connection, or paste for session. Mentions calling with no args to get link. Lacks explicit 'when not to use' but is mostly sufficient.
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 separated by resource and verb, but there are several borderline pairs: list_transactions vs list_transactions_by_item, get_item_status vs list_connections vs provider_status, and list_accounts vs get_account_balance. The marketplace tool also bundles search/describe/invoke/install/report_bug/prompt-library actions, which overlaps with standalone report_bug and adds confusion.
The openfinance_* family follows a clean get_/ list_/ update_ pattern, but the platform tools mix bare verbs like connect and authenticate with noun-style names like marketplace and toolkit_info. This split is readable but not a single consistent convention.
25 tools sits at the upper end of the 16-25 'heavy' band. The Open Finance domain genuinely has many resources and the openfinance_* tools mostly earn their place, but the generic platform tools plus the multi-purpose marketplace make the set feel larger than its core purpose requires.
The Open Finance lifecycle is well covered: connection search/link/status/sync/disconnect, accounts/balances/detail, transactions with categorization, credit-card bills with derived payment status, loans, and investments with transaction history. Minor gaps exist, such as no standalone connect/install tools, but those flows are handled via URLs and embedded marketplace actions rather than missing entirely.