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 adds behavioral context beyond annotations by explaining session vs. permanent modes and that calling with no args returns a link. It does not contradict the idempotentHint; it adds meaningful detail about the two invocation styles.
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 but somewhat long sentence with a colon, delivering purpose and usage in a compact form. It is front-loaded with the main action and avoids unnecessary fluff, though it could be split more cleanly.
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?
Given the tool has one optional parameter and no output schema, the description covers the main usage modes and expected result (link). It lacks error handling details or response format, but for this simple auth tool it is reasonably 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 provides a bare 'token' string with no description. The description fills this gap by explaining the token is a JWT and that it can be omitted to get a link. This meaningfully compensates for the 0% schema description 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's purpose: authenticate a user by logging in via browser and using an access token. It distinguishes itself from siblings by being the only authentication tool, and it describes the specific flow (get link, paste token) rather than being vague.
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?
It provides explicit usage guidance: the best approach (add to config for permanent connection) and an alternative (paste token for session-only login). It also explains when to call with no args to get the link, giving clear context on how to use the 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.
Most tools have clearly distinct purposes, especially within the openfinance_* group (list vs get vs sync vs status). A few potential overlaps exist (e.g., openfinance_list_transactions vs openfinance_list_transactions_by_item, openfinance_get_account_balance vs openfinance_list_accounts), but descriptions are detailed enough to guide correct selection.
The openfinance_* tools follow a consistent verb_noun pattern (e.g., openfinance_list_accounts, openfinance_get_item_status). However, non-openfinance tools (authenticate, connect, marketplace, toolkit_info) use a different style, and one tool (openfinance_list_transactions_by_item) breaks the pattern slightly. Overall readable and predictable within the primary domain.
With 25 tools, the count is on the heavy side per the calibration rubric (16-25 feels heavy). The server covers a broad financial data domain, which justifies the number, but it may present a steep learning curve and potential overwhelm for agents.
The tool surface is comprehensive for read-only Open Finance data access: accounts, transactions, balances, bills, loans, investments, category management, connection lifecycle, and status monitoring. Minor gaps exist (e.g., no direct payment initiation, no investment transaction creation), but for the stated purpose of data and analysis, coverage is strong.