Skip to main content
Glama

Carrefour MCP

by io.github.mcp-dir

openfinance_force_sync

Forces the bank to re-sync one or more connections NOW and WAITS for it to finish (PATCH /items/:id, then polls until the item stops updating, up to ~60s). Use this when a balance or transaction list looks stale: a connection can read UPDATED yet be hours old, and this pulls fresh data WITHOUT disconnecting/reconnecting. Pass items as an array of selectors (item_id, connector_id, connector_name, or the user-set custom_label nickname); OMIT items to sync ALL linked banks. Returns { results, errors }; each result has the final status, executionStatus, lastUpdatedAt (advances when data is refreshed), and synced (true = fresh data is ready). needs_action (e.g. MFA_REINTERACTION / LOGIN_ERROR / WAITING_USER_INPUT) means the user must re-authenticate — those results include a reconnect_url that opens the widget in UPDATE mode for that exact connection (user enters credentials / MFA token, data refreshes in place, no slot consumed, no disconnect needed). timed_out: true means the sync is still running — re-check with openfinance_get_item_status. Set wait: false for fire-and-forget (returns immediately while UPDATING).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNo
itemsNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Goes far beyond annotations (which only indicate not read-only, not destructive). Describes polling behavior (waits up to ~60s), return fields (status, executionStatus, lastUpdatedAt, synced, needs_action with reconnect_url), error states (MFA_REINTERACTION, LOGIN_ERROR, timed_out). No contradictions 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 longer than average but every sentence adds value. It is front-loaded with the main action and then provides detailed guidance. Could be slightly more concise but remains clear and well-structured.

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

Completeness5/5

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

Given no output schema, the description thoroughly explains the return format (results/errors) with field meanings and error handling (reconnect_url, timed_out). It covers all essential behavioral aspects for an agent to use the tool correctly.

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

Parameters5/5

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

Despite 0% schema coverage, the description fully explains both parameters: 'items' as an array of selectors (item_id, connector_id, etc.) and that omitting it syncs all; 'wait' as a boolean for synchronous vs fire-and-forget. This fully compensates for the missing schema descriptions.

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?

The description uses specific verbs ('forces', 're-sync') and resource ('connections') and clearly states it waits for completion. It distinguishes itself from sibling tools like openfinance_get_item_status (re-check if timed out) and read-only tools by emphasizing its write/sync nature.

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

Usage Guidelines5/5

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

Explicitly tells when to use (stale balance/transactions) and when not to (without disconnecting). Mentions alternatives (openfinance_get_item_status for timed out results) and provides guidance on wait parameter behavior (fire-and-forget vs wait).

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

All Carrefour 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

A4.1/5.0
Disambiguation4/5

The openfinance_* cluster maps cleanly to distinct resources/actions and the descriptions sharply separate lookalikes like openfinance_get_item_status vs openfinance_provider_status. A few boundaries are fuzzy: openfinance_list_transactions_by_item overlaps with openfinance_list_transactions, marketplace also exposes report_bug alongside the standalone report_bug tool, and get_account_balance/list_accounts both return balances.

Naming Consistency4/5

The 20 finance tools consistently follow openfinance_<verb>_<noun> (list_accounts, get_credit_card_bill, force_sync, update_transaction_category), which is the dominant pattern. The five platform tools break it with bare verbs and nouns (connect, marketplace, toolkit_info, show_version), creating a clear but minor namespace split.

Tool Count4/5

25 tools is at the heavy end of the typical range, but the server covers two substantial domains (Open Finance data and an MCP marketplace/platform), so most tools earn their place. There is little redundant surface; the only mild overreach is marketplace smuggling many sub-operations into one tool.

Completeness4/5

The Open Finance surface is remarkably complete: accounts, balances, transactions, credit card bills, loans, investments, categories, connection health, force sync, connector search, and disconnect. Minor gaps remain, such as no direct programmatic bank-connection creation tool (URLs are returned instead) and no singular transaction/get-investment-detail endpoint, but agents can work around these.

Resources