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 already indicate idempotentHint=true and destructiveHint=false. Description adds that calling with no args returns a link, and with token sets session login. 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?
Description is moderately concise, front-loads core purpose. Sentences are efficient though slightly verbose with alternative config advice.
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 an authentication tool with no output schema, description covers both session and permanent modes, expected user actions, and output (link or success). Complete for intended use.
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 string 'token' with 0% coverage. Description explains its meaning: paste token for session login or omit to get login link, providing essential semantics missing from 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?
Description clearly states the tool authenticates IDE agents to MCP.AI, explaining login methods and token usage. It is a distinct authentication tool among siblings.
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?
Description explains when to use: for logging in via browser and obtaining a token, either as persistent header or session. It gives explicit steps but does not mention when not to use or compare to siblings like 'connect'.
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_* family is mostly well-differentiated by resource type, but several tools overlap in purpose: openfinance_get_account_balance, openfinance_get_accounts_detail, and openfinance_list_accounts all return account/balance data, and openfinance_list_transactions versus openfinance_list_transactions_by_item have similar scopes. The marketplace tool also bundles many sub-actions (search, invoke, install, subscribe, report_bug, prompt library) into one tool, and duplicates the standalone report_bug tool. Detailed descriptions help, but an agent could easily misselect among the account and transaction variants.
Naming is largely consistent: the finance tools follow a clear openfinance_verb_noun pattern (list_accounts, get_account_balance, force_sync, update_transaction_category). There are minor singular/plural inconsistencies (get_account_balance vs get_accounts_detail, get_credit_card_bill vs list_credit_card_bills) and generic platform verbs like authenticate/connect/marketplace that follow a different style, but the overall pattern is predictable and readable.
25 tools is at the upper boundary of what feels manageable for a server covering platform management, marketplace operations, and a broad Open Finance data domain. The count is defensible given the many resource types (accounts, transactions, bills, loans, investments, connections), but it is heavy and the marketplace tool alone packs a dozen sub-capabilities into one entry, making the surface feel larger than 25 discrete tools.
The Open Finance surface is quite complete: connection lifecycle (list, connect, disconnect, force sync, status, provider status), account and balance reads, transactions with categorization support, credit card bills with payment status, loans, investments, and investment transactions. Platform concerns like authentication, versioning, toolkit state, marketplace search/install/invoke, and bug reporting are also covered, leaving no obvious dead ends for the server's stated purpose.