Skip to main content
Glama
matteoantoci

MCP Bitpanda Server

list_fiat_transactions

Retrieve and manage your fiat currency transaction history from Bitpanda, including buys, sells, deposits, and withdrawals with paginated results.

Instructions

Lists all user's fiat transactions from the Bitpanda API. Newest fiat transactions come first. Response is cursor paginated.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNobuy, sell, deposit, withdrawal, transfer, refund
statusNopending, processing, finished, canceled
cursorNoId of the last known fiat transaction by the client. Only fiat transactions after this id are returned. Empty or missing cursor parameter will return fiat transactions from the start.
page_sizeNoSize of a page for the paginated response

Implementation Reference

  • The main handler function for the 'list_fiat_transactions' tool. It constructs API parameters from input, makes a GET request to the Bitpanda fiat transactions endpoint using axios, and returns the paginated response or throws an error.
    const listFiatTransactionsHandler = async (input: Input): Promise<Output> => {
      try {
        const apiKey = getBitpandaApiKey();
        const url = `${BITPANDA_API_BASE_URL}/fiatwallets/transactions`;
    
        const params: any = {}; // Use any for now, refine later if needed
        if (input.type) {
          params.type = input.type;
        }
        if (input.status) {
          params.status = input.status;
        }
        if (input.cursor) {
          params.cursor = input.cursor;
        }
        if (input.page_size) {
          params.page_size = input.page_size;
        }
    
        const response = await axios.get<Output>(url, {
          headers: {
            'X-Api-Key': apiKey,
            'Content-Type': 'application/json',
          },
          params,
        });
    
        // Return the data received from the Bitpanda API
        return response.data;
      } catch (error: unknown) {
        console.error('Error fetching Bitpanda fiat transactions:', error);
        const message =
          error instanceof Error ? error.message : 'An unknown error occurred while fetching fiat transactions.';
        // Re-throwing the error to be handled by the MCP server framework
        throw new Error(`Failed to fetch Bitpanda fiat transactions: ${message}`);
      }
    };
  • Zod-based input schema shape for validating the tool's parameters: type (transaction type), status, cursor (pagination), and page_size.
    const listFiatTransactionsInputSchemaShape = {
      type: z
        .enum(['buy', 'sell', 'deposit', 'withdrawal', 'transfer', 'refund'])
        .optional()
        .describe('buy, sell, deposit, withdrawal, transfer, refund'),
      status: z
        .enum(['pending', 'processing', 'finished', 'canceled'])
        .optional()
        .describe('pending, processing, finished, canceled'),
      cursor: z
        .string()
        .optional()
        .describe(
          'Id of the last known fiat transaction by the client. Only fiat transactions after this id are returned. Empty or missing cursor parameter will return fiat transactions from the start.'
        ),
      page_size: z.number().int().positive().optional().describe('Size of a page for the paginated response'),
    };
  • Tool definition object exporting the name, description, input schema, and handler for registration.
    export const listFiatTransactionsTool: BitpandaToolDefinition = {
      name: 'list_fiat_transactions',
      description:
        "Lists all user's fiat transactions from the Bitpanda API. Newest fiat transactions come first. Response is cursor paginated.",
      inputSchemaShape: listFiatTransactionsInputSchemaShape,
      handler: listFiatTransactionsHandler,
    };
  • Array of all tool definitions, including listFiatTransactionsTool, used for batch registration.
    const bitpandaToolDefinitions: BitpandaToolDefinition[] = [
      listTradesTool, // Add the listTradesTool to the array
      listAssetWalletsTool, // Add the listAssetWalletsTool to the array
      listFiatWalletsTool, // Add the listFiatWalletsTool to the array
      listFiatTransactionsTool, // Add the listFiatTransactionsTool to the array
      listCryptoWalletsTool, // Add the listCryptoWalletsTool to the array
      listCryptoTransactionsTool, // Add the listCryptoTransactionsTool to the array
      listCommodityTransactionsTool, // Add the listCommodityTransactionsTool to the array
      assetInfoTool, // Add the assetInfoTool to the array
      // ohlcTool, // Add the ohlcTool to the array
      // Other tools will be added here as they are implemented
    ];
  • Function that registers all Bitpanda tools (including list_fiat_transactions) to the MCP server instance by calling server.tool() for each.
    export const registerBitpandaTools = (server: McpServer): void => {
      bitpandaToolDefinitions.forEach((toolDef) => {
        try {
          // Pass the raw shape to the inputSchema parameter, assuming SDK handles z.object()
          server.tool(toolDef.name, toolDef.description, toolDef.inputSchemaShape, async (input) => {
            const result = await toolDef.handler(input);
            // Assuming the handler returns the data directly, wrap it in the MCP content format
            return {
              content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
            };
          });
          console.log(`Registered Bitpanda tool: ${toolDef.name}`);
        } catch (error) {
          console.error(`Failed to register tool ${toolDef.name}:`, error);
        }
      });
    };
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: it specifies that results are ordered newest-first and cursor-paginated. However, it doesn't cover critical aspects like authentication requirements, rate limits, error handling, or what the response format looks like, leaving gaps for a tool with no annotation support.

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

Conciseness5/5

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

The description is front-loaded with the core purpose in the first sentence, followed by two concise sentences adding key behavioral details (ordering and pagination). Every sentence earns its place with no wasted words, making it efficient and well-structured.

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

Completeness3/5

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

Given no annotations and no output schema, the description is moderately complete: it covers purpose, ordering, and pagination but lacks details on authentication, error handling, response format, and usage guidelines. For a list tool with 4 parameters and no structured support, it should do more to compensate for these gaps.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional meaning beyond what the schema provides, such as explaining parameter interactions or usage examples. Baseline 3 is appropriate when the schema handles all parameter documentation.

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 clearly states the verb ('Lists') and resource ('all user's fiat transactions from the Bitpanda API'), specifying the scope and data source. It distinguishes from siblings like list_crypto_transactions by focusing on fiat transactions, making the purpose specific and well-defined.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, such as list_crypto_transactions or list_trades. It lacks context about use cases, prerequisites, or exclusions, leaving the agent without direction for tool selection among siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/matteoantoci/mcp-bitpanda'

If you have feedback or need assistance with the MCP directory API, please join our Discord server