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?
The description reveals that setting a permanent token in config is non-expiring, and session login is per-session. It matches annotations (idempotentHint, destructiveHint false) and adds context about the token's lifetime.
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 that effectively conveys the two methods, but it could be more structured (e.g., separate bullet points) and is slightly informal.
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?
The description explains inputs and behavior but does not describe the output (e.g., format of the returned link) or error cases. Given the simplicity, it is adequate but not fully complete.
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 schema only defines 'token' as a string with no description. The description adds crucial meaning: omitting it yields a login link, including it authenticates. This compensates for 0% schema coverage.
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 (logging in) and specifies two methods: permanent via config or session via token. It targets IDE agents, but does not explicitly distinguish 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?
The description explains two ways to use the tool (with no args to get link, or with token to authenticate), but does not compare to alternative tools or indicate when to use which method.
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_* cluster is mostly well separated, but openfinance_list_transactions and openfinance_list_transactions_by_item overlap, and several platform tools (authenticate, connect, marketplace, toolkit_info) all touch status/auth/connection concepts. Long descriptions mitigate but don't eliminate misselection risk.
The 18 Open Finance tools follow a consistent openfinance_verb_noun convention; only the handful of platform tools deviate with bare verbs/nouns. The pattern is predictable within each group.
25 tools sits at the heavy end of the range; the Open Finance data surface justifies a large set, but the extra marketplace/status tools add breadth. It's still navigable though.
The Open Finance surface covers connections, accounts, balances, transactions, credit-card bills, loans, investments, category correction, sync, and provider health. Missing direct connection creation and some write operations, but connect_urls and reconnect/force-sync close most gaps.