Skip to main content
Glama
covalenthq

GoldRush MCP Server

by covalenthq

multichain_transactions

Fetch paginated transaction history for multiple EVM addresses across multiple blockchain networks in a single API call. Analyze cross-chain activity and build activity feeds with optional logs and value conversion.

Instructions

Fetch paginated transactions for up to 10 EVM addresses and 10 EVM chains with one API call. Useful for building Activity Feeds. Requires addresses array. Optional parameters include chains array, pagination (before/after), limit (default 10), quoteCurrency for value conversion, and options to include logs (withLogs, withDecodedLogs). Use this to analyze transaction history across different networks simultaneously.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chainsNoArray of blockchain networks to query. Can be chain names (e.g., 'eth-mainnet') or chain IDs (e.g., 1). If not specified, queries all supported chains.
addressesNoArray of wallet addresses to get transactions for. Each address should be a valid blockchain address.
limitNoMaximum number of transactions to return per request. Default is 10, maximum is 100.
beforeNoPagination cursor to get transactions before this point. Use the 'before' value from previous response.
afterNoPagination cursor to get transactions after this point. Use the 'after' value from previous response.
withLogsNoInclude transaction logs in the response. Default is false.
withDecodedLogsNoInclude decoded transaction logs in the response. Only applicable when withLogs is true. Default is false.
quoteCurrencyNoCurrency to quote token values in (e.g., 'USD', 'EUR'). If not specified, uses default quote currency.

Implementation Reference

  • The handler for the multichain_transactions tool, which executes the GoldRush client call to getMultiChainMultiAddressTransactions.
    async (params) => {
        try {
            const response =
                await goldRushClient.AllChainsService.getMultiChainMultiAddressTransactions(
                    {
                        chains: params.chains as Chain[],
                        addresses: params.addresses,
                        limit: params.limit,
                        before: params.before,
                        after: params.after,
                        withLogs: params.withLogs,
                        withDecodedLogs: params.withDecodedLogs,
                        quoteCurrency: params.quoteCurrency as Quote,
                    }
                );
            return {
                content: [
                    {
                        type: "text",
                        text: stringifyWithBigInt(response.data),
                    },
                ],
            };
        } catch (error) {
            return {
                content: [{ type: "text", text: `Error: ${error}` }],
                isError: true,
            };
        }
    }
  • Input schema validation for the multichain_transactions tool using Zod.
    {
        chains: z
            .array(
                z.union([
                    z.enum(
                        Object.values(ChainName) as [string, ...string[]]
                    ),
                    z.number(),
                ])
            )
            .optional()
            .describe(
                "Array of blockchain networks to query. Can be chain names (e.g., 'eth-mainnet') or chain IDs (e.g., 1). If not specified, queries all supported chains."
            ),
        addresses: z
            .array(z.string())
            .optional()
            .describe(
                "Array of wallet addresses to get transactions for. Each address should be a valid blockchain address."
            ),
        limit: z
            .number()
            .optional()
            .default(10)
            .describe(
                "Maximum number of transactions to return per request. Default is 10, maximum is 100."
            ),
        before: z
            .string()
            .optional()
            .describe(
                "Pagination cursor to get transactions before this point. Use the 'before' value from previous response."
            ),
        after: z
            .string()
            .optional()
            .describe(
                "Pagination cursor to get transactions after this point. Use the 'after' value from previous response."
            ),
        withLogs: z
            .boolean()
            .optional()
            .default(false)
            .describe(
                "Include transaction logs in the response. Default is false."
            ),
        withDecodedLogs: z
            .boolean()
            .optional()
            .default(false)
            .describe(
                "Include decoded transaction logs in the response. Only applicable when withLogs is true. Default is false."
            ),
        quoteCurrency: z
            .enum(Object.values(validQuoteValues) as [string, ...string[]])
            .optional()
            .describe(
                "Currency to quote token values in (e.g., 'USD', 'EUR'). If not specified, uses default quote currency."
            ),
    },
  • Registration of the multichain_transactions tool within the MCP server.
    server.tool(
        "multichain_transactions",
        "Fetch paginated transactions for up to 10 EVM addresses and 10 EVM chains with one API call. Useful for building Activity Feeds. " +
            "Requires addresses array. Optional parameters include chains array, " +
            "pagination (before/after), limit (default 10), quoteCurrency for value conversion, " +
            "and options to include logs (withLogs, withDecodedLogs). " +
            "Use this to analyze transaction history across different networks simultaneously.",
        {
            chains: z
                .array(
                    z.union([
                        z.enum(
                            Object.values(ChainName) as [string, ...string[]]
                        ),
                        z.number(),
                    ])
                )
                .optional()
                .describe(
                    "Array of blockchain networks to query. Can be chain names (e.g., 'eth-mainnet') or chain IDs (e.g., 1). If not specified, queries all supported chains."
                ),
            addresses: z
                .array(z.string())
                .optional()
                .describe(
                    "Array of wallet addresses to get transactions for. Each address should be a valid blockchain address."
                ),
            limit: z
                .number()
                .optional()
                .default(10)
                .describe(
                    "Maximum number of transactions to return per request. Default is 10, maximum is 100."
                ),
            before: z
                .string()
                .optional()
                .describe(
                    "Pagination cursor to get transactions before this point. Use the 'before' value from previous response."
                ),
            after: z
                .string()
                .optional()
                .describe(
                    "Pagination cursor to get transactions after this point. Use the 'after' value from previous response."
                ),
            withLogs: z
                .boolean()
                .optional()
                .default(false)
                .describe(
                    "Include transaction logs in the response. Default is false."
                ),
            withDecodedLogs: z
                .boolean()
                .optional()
                .default(false)
                .describe(
                    "Include decoded transaction logs in the response. Only applicable when withLogs is true. Default is false."
                ),
            quoteCurrency: z
                .enum(Object.values(validQuoteValues) as [string, ...string[]])
                .optional()
                .describe(
                    "Currency to quote token values in (e.g., 'USD', 'EUR'). If not specified, uses default quote currency."
                ),
        },
Behavior3/5

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

No annotations provided, so description carries full burden. It discloses pagination behavior (before/after cursors), default values (limit: 10), and critical constraints (10 address/chain max). However, it omits safety classification (read-only vs destructive), error handling behavior, and rate limiting details expected for unannotated data retrieval tools.

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?

Four sentences efficiently structured: scope definition, use case, requirements, and optional parameters. Front-loaded with key constraints (10/10 limits). Minor redundancy in listing optional parameters that are well-documented in schema, but earns its place by adding the 10-limit context.

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?

Covers main functionality and constraints well, but has a discrepancy with schema metadata (description states 'Requires addresses array' while schema indicates 0 required parameters). Also lacks description of return values/output format, which is notably absent given no output schema exists and the tool returns complex paginated data.

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?

While schema has 100% description coverage (baseline 3), the description adds crucial constraint semantics not in schema: the 'up to 10' limit for addresses and chains. It also clarifies required vs optional parameters and organizes them logically, adding value beyond raw schema 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?

Description opens with specific verb 'Fetch' + resource 'paginated transactions' + clear scope constraints 'up to 10 EVM addresses and 10 EVM chains'. Explicitly distinguishes from single-chain sibling tools like 'transactions_for_address' by emphasizing 'multichain' and 'with one API call'.

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?

Provides clear context for when to use ('Useful for building Activity Feeds', 'analyze transaction history across different networks simultaneously'), implying multi-address/multi-chain scenarios. However, lacks explicit 'when not to use' guidance or named alternative tools for simpler single-chain queries.

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/covalenthq/goldrush-mcp-server'

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