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 and destructiveHint=false, but the description adds behavioral context: it returns a login link when called without token, and performs authentication when called with token. This goes beyond annotations.
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 two sentences, front-loaded with purpose, and covers both usage scenarios efficiently. While slightly informal with phrases like 'best:' and 'Or paste it here', it is not wasteful.
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 one-parameter tool with no output schema, the description provides complete context: how to use it, what the token is, and the two authentication workflows. All necessary information is present.
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 one optional parameter 'token' with 0% description coverage. The description compensates by explaining the token is a JWT from browser login, and that omitting it returns a link. This clearly defines the parameter's role.
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 handles authentication for MCP.AI IDE agents, distinguishing it from sibling tools that deal with connections, marketplace, and other functions. It specifies two authentication methods: permanent config or session token.
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 explicitly explains when to use the tool (for login) and provides two alternatives: adding token to config for permanent access, or pasting a JWT for session-only login. It also states calling with no arguments yields a login link.
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 clearly separated by resource and action—accounts, transactions, bills, loans, investments, and connection status—so an agent can usually tell them apart. A few pairs remain confusable, notably openfinance_list_transactions vs openfinance_list_transactions_by_item and the monolithic marketplace tool overlapping with report_bug, but the detailed descriptions largely resolve the boundaries.
The openfinance_* subset follows a consistent snake_case verb_noun convention (list_accounts, get_item_status, update_transaction_category), and non-openfinance tools like report_bug and show_version fit the same style. The pattern breaks with bare verbs/nouns such as connect, authenticate, marketplace, and toolkit_info, but the domain prefix makes the majority predictable.
25 tools sits at the top of the heavy-but-manageable range, and the Open Finance resource pairs plus platform/marketplace tools each earn some place. The count feels slightly bloated because marketplace bundles many capabilities and several status/sync tools could be consolidated, but the scope is broad enough that the number is defensible.
The toolkit covers the core Open Finance surface thoroughly: accounts, balances, transactions, credit-card bills, loans, investments, categories, connection lifecycle, sync, and provider health, plus marketplace and platform plumbing. Minor gaps exist—no direct connect-bank action beyond URLs, no per-transaction get endpoint, and some marketplace operations are only accessible through the single marketplace tool—but standard workflows are not dead-ended.