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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations show idempotentHint=true and destructiveHint=false. Description adds behavioral context: tool can return a link (no side effect) or authenticate with token (side effect). No contradiction; further clarifies session vs permanent behavior.
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 providing distinct value: purpose, best practice, usage details. Slightly verbose but no wasted words. Well front-loaded with key action.
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?
No output schema, so description must clarify return values. It implies returning a link with no args but doesn't specify output format or error handling. For a simple auth tool, this is adequate but incomplete.
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 token parameter with no description (0% coverage). Description fully explains its purpose: session-only login when provided, and that omitting it returns a login link. Adds essential semantics.
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 specifies the tool's purpose: authentication via browser login and token copy. It differentiates between permanent config and session-only usage, making the verb and resource explicit. No ambiguity.
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 usage guidance: best practice to add config header for permanent connection, or paste token for session. Also explains call variants (no args for link, with token for login). Clear when to use each option.
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 target distinct resources and operations (balance, accounts, loans, investments, connections, provider status), but credit card bill handling is split across three overlapping tools (get_credit_card_bill, list_credit_card_bills, list_transactions), which could cause misselection. The platform-level tools (authenticate, connect, marketplace, etc.) are clearly distinct from the finance tools.
The openfinance_* tools mostly follow a verb_noun snake_case pattern (list_accounts, get_account_balance, update_transaction_category), but a few deviate (openfinance_provider_status, openfinance_search_bank_connectors). The non-prefixed platform tools break the pattern entirely with mixed styles: verbs (connect, authenticate), nouns (marketplace), and noun_verb (report_bug, show_version).
At 25 tools, this sits at the high end of reasonable scope. Each Open Finance tool maps to a specific endpoint or workflow, and the platform tools are needed for the MCP meta-layer, but the sheer number makes the set feel heavy and harder to navigate.
The Open Finance surface is thorough: connection lifecycle, accounts, balances, transactions, credit card bills, loans, investments, categories, and provider health. Minor gaps exist (e.g., no webhook management, no bulk CSV export), but core workflows are well covered and there are no dead ends.