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?
Adds useful context beyond annotations: distinguishes permanent non-expiring connections from session-only logins, and discloses that calling with no args returns a link. Annotations only provide idempotentHint; the description offers practical behavioral details that help the agent understand side effects.
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?
A three-sentence paragraph that is informative and structured, though the opening context 'MCP.AI for IDE agents' is slightly verbose. No redundant wording, and the flow from browser login to two authentication options is logical.
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 simple tool with one optional parameter, the description covers how to use it and the behavior of each mode. It lacks explicit return value descriptions for the token call, but that is not critical for the agent to invoke the tool correctly.
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?
Despite 0% schema description coverage, the description fully explains the optional 'token' parameter: it is the JWT to paste for session-only login, while omitting it fetches the link. This completely compensates for the bare 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 action: authenticate with the server by logging in via browser and handling access tokens. It distinguishes itself from sibling tools as the sole authentication tool and explains the two invocation modes (permanent header 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?
Provides clear context for IDE agents (Cursor, etc.) and explicitly describes two usage modes: permanent header configuration and session-only token pasting. It does not contrast with sibling tools like 'connect', but the guidance on when to use each mode is clear.
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 largely well-differentiated by resource and action, but the monolithic `marketplace` tool bundles search, invoke, install, billing, and prompt-library actions into one name, creating ambiguity about where platform capabilities live. Additionally, `openfinance_list_transactions` and `openfinance_list_transactions_by_item` both return transaction data and could be misselected despite their different aggregation intent.
The openfinance_* tools consistently follow a clear verb_noun pattern, which gives the majority of the surface a predictable shape. But the generic platform tools mix bare verbs (`authenticate`, `connect`), nouns (`marketplace`, `toolkit_info`), and verb_noun names (`report_bug`, `show_version`), so the server has two naming dialects rather than one uniform convention.
At 25 tools, this sits right at the top of the heavy range, and the server genuinely spans two broad domains: MCP platform administration and Open Finance banking data. The count is defensible given the breadth, but it is not a lean or easily navigable surface for an agent.
The Open Finance side is quite complete, covering connections, accounts, transactions, credit card bills, loans, investments, categories, provider status, sync, and disconnection. The platform side covers authentication, connection status, marketplace operations, bug reporting, and versioning, though some marketplace sub-actions are packed into one tool and bank connection itself is only reachable through URLs returned by other tools.