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 declare idempotentHint=true, and description reinforces idempotency by noting calling with no args gives link. Description adds behavioral context beyond annotations (browser login flow, permanent vs session). No contradiction.
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 sentences, each essential. Front-loaded with purpose, then usage, then parameter behavior. No filler, every sentence earns its place.
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 no output schema, the description covers the entire authentication flow. Lacks error handling details, but acceptable given pro-level 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 single optional parameter 'token' is thoroughly explained: used for pasting JWT from browser, or omitted to get login link. Schema coverage is 0%, but description fully compensates with clear meaning.
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: authentication for MCP.AI IDE agents. It explains two modes (permanent token via config, session token via argument) and distinguishes from sibling tools by being the only 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?
Provides explicit instructions on when to use each authentication method, including best practice (config) and session-only option. Does not explicitly state when not to use, but contextually clear it's the sole authentication 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.
Several tools have overlapping purviews—list_transactions vs list_transactions_by_item, get_credit_card_bill vs list_credit_card_bills, and connect vs list_connections vs get_item_status vs provider_status—so an agent could pick the wrong one. The very detailed descriptions disambiguate them, but the tool names alone do not.
The openfinance_ prefix provides a clear family and most members use list_/get_/update_ verbs, but there are deviations like openfinance_provider_status (no verb), openfinance_disconnect_bank, and openfinance_force_sync. Platform tools (authenticate, connect, marketplace, toolkit_info) follow a different, less uniform style.
At 25 tools, this sits at the top of the heavy range. Most Open Finance operations are justified given the breadth of banking data, but overlapping tools and the mega-marketplace tool with many sub-actions make the set feel slightly bloated.
The Open Finance surface covers list/get/update/disconnect/sync for accounts, transactions, credit card bills, loans, and investments, plus provider health, connection search, and platform-level auth, marketplace, version, and feedback. There are no obvious dead ends or missing lifecycle operations.