Skip to main content
Glama

Caixa Tem MCP

by io.github.mcp-dir

openfinance_get_account_balance

Read-onlyIdempotent

Returns the latest available balance per account id (GET /accounts/:id/balance). This is the freshest balance the provider can serve, but it is a SNAPSHOT anchored to the connection's last upstream sync: the updateDateTime/updatedAt in each row is that sync instant, NOT a to-the-second live read. If a movement that just happened is not reflected yet, or the balance disagrees with the sum of openfinance_list_transactions, run openfinance_force_sync to pull fresh data and then re-read. Pass account_ids as an array (1–50). CREDIT accounts may return Pluggy BALANCE_FETCH_ERROR (provider could not fetch it) or BALANCE_CONSENT_ERROR (the institution refused it because the consent lacks the balance permission — reconnecting the bank restores it) — those rows include a structured warning instead of throwing. When the financial institution is temporarily unavailable upstream (5xx) or the connector is not Open Finance, the row DEGRADES to the last-synced balance with realtime: false, updatedAt and a warning instead of an error. Response shape: { results: [...], errors: [{ id, status, message }] }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
account_idsYes

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool read-only and idempotent. The description adds substantial behavioral context: the balance is a snapshot of the last upstream sync rather than a live read, credit accounts may return structured warnings for BALANCE_FETCH_ERROR/BALANCE_CONSENT_ERROR, and non-Open-Finance or 5xx upstream failures degrade gracefully. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but not wasteful: it front-loads purpose, then covers freshness caveats, error modes, and usage constraints. Every sentence adds operational value, though it is on the longer side for a one-parameter read tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description effectively covers what an agent needs: snapshot timing, response row fields (updateDateTime/updatedAt, warning), error modes, and array limits. It stops short of providing the full response JSON shape, but the available detail is sufficient for correct invocation and interpretation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It provides the 1–50 array constraint for account_ids and clarifies that the parameter must be passed as an array. The meaning of account IDs is left implicit, but the parameter name is self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Returns'), resource ('latest available balance per account id'), and endpoint (GET /accounts/:id/balance). It also differentiates from siblings like openfinance_list_transactions and openfinance_force_sync by positioning what this tool uniquely provides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit guidance to run openfinance_force_sync when balances are stale or disagree with openfinance_list_transactions, then re-read. It also constrains account_ids to 1–50. It does not explicitly state when not to use the tool, but the alternative path is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Caixa Tem MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation3/5

The openfinance_* tools are mostly distinct, but several have overlapping boundaries: openfinance_list_transactions vs openfinance_list_transactions_by_item, openfinance_get_item_status vs openfinance_provider_status, and openfinance_list_accounts carrying balance vs openfinance_get_account_balance. The platform-level tools also blur somewhat: marketplace, toolkit_info, and connect all touch installed or available services.

Naming Consistency3/5

The openfinance_* group follows a consistent list/get/update verb pattern in snake_case, but platform-level tools like authenticate, connect, marketplace, report_bug, show_version, and toolkit_info break that convention. The set is readable, but it is split between two clearly different naming styles.

Tool Count3/5

At 25 tools, the server is at the heavy end, and several are platform/MCP-management helpers rather than core banking capabilities. The count is not absurd for a broad Open Finance + marketplace adapter, but it feels more cluttered than a focused financial data toolset should be.

Completeness4/5

The Open Finance surface is thorough: accounts, transactions, balances, credit card bills, loans, investments, connection lifecycle, sync, provider status, and category correction are all covered. The main gaps are the absence of a direct connect/create action (only URLs are returned) and no write operations beyond category updates, but for a read-centric financial data adapter this is close to complete.

Resources