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 provide readOnlyHint=false (write), destructiveHint=false, idempotentHint=true. Description adds context: explains login flow, token expiration (session-only), permanent vs temporary. It also reveals that calling with no args returns a link. No contradictions.
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 slightly verbose (three sentences) but front-loads the purpose. Every sentence adds value, though it could be condensed slightly. Still efficient.
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's simplicity (one optional param, no output schema), the description is fully complete. Covers both authentication methods, explains token behavior, and mentions config alternative. No gaps.
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 coverage is 0%, but description fully explains the single parameter 'token': optional JWT string. It describes both use cases: with token for authentication, without for getting login link. Adds meaning beyond schema.
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: authenticating via browser login and token. It specifies the verb 'authenticate' and the resource 'access token', and distinguishes between two methods (permanent config vs session-only paste). This differentiates it from sibling tools like 'connect' or 'marketplace'.
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 guidance: best practice is to add token to config for permanent connection; alternative is to paste token for session-only login. It explains calling with token (paste) or without (get link), covering both scenarios. No exclusions needed.
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.
Every tool has a clearly distinct purpose: accounts, transactions, credit card bills, loans, investments, connections, sync, categories, provider status, and platform meta-tools are all separable. Even the two transaction tools differ (per-account list vs consolidated analysis) and the two status tools differ (connection vs provider health).
The openfinance_* prefix is consistently applied across the financial domain, and most follow a verb_noun pattern (list_accounts, get_balance, update_category). However, there are non-prefixed tools (authenticate, connect, marketplace, toolkit_info) and one outlier like openfinance_provider_status (noun instead of verb) that slightly break the pattern.
25 tools is at the upper boundary of what feels heavy for a single server, even for a comprehensive financial aggregation toolkit. The number is justified by the breadth of domains covered (accounts, credit, loans, investments, connections, platform features), but it requires careful agent selection and might be better split into separate servers.
The surface covers the full financial data lifecycle: listing and fetching details for all asset types, updating transaction categories, managing connections (list, sync, disconnect, reauth), checking provider health, and searching connectors. There are no obvious dead ends—every domain has read and appropriate write/update operations.