Skip to main content
Glama

list_offchain_actions

Filter and retrieve off-chain action history by venue and status using pagination.

Instructions

List off-chain action history (signedData/signedHttp) with venue/status filter and pagination.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
venueNoFilter by venue name (e.g. polymarket, hyperliquid)
statusNoFilter by status (e.g. PENDING, FILLED, CANCELED, EXPIRED)
limitNoMaximum number of results to return
offsetNoPagination offset
wallet_idNoWallet ID. Auto-resolved for single-wallet sessions.

Implementation Reference

  • The registerListOffchainActions function registers the 'list_offchain_actions' MCP tool. The handler (lines 32-42) extracts optional filters (venue, status, limit, offset) from args, builds URLSearchParams, and calls apiClient.get on the /v1/wallets/{walletId}/actions endpoint, returning the result via toToolResult.
    export function registerListOffchainActions(
      server: McpServer,
      apiClient: ApiClient,
      walletContext?: WalletContext,
    ): void {
      server.tool(
        'list_offchain_actions',
        withWalletPrefix(
          'List off-chain action history (signedData/signedHttp) with venue/status filter and pagination.',
          walletContext?.walletName,
        ),
        {
          venue: z.string().optional().describe('Filter by venue name (e.g. polymarket, hyperliquid)'),
          status: z.string().optional().describe('Filter by status (e.g. PENDING, FILLED, CANCELED, EXPIRED)'),
          limit: z.number().optional().describe('Maximum number of results to return'),
          offset: z.number().optional().describe('Pagination offset'),
          wallet_id: z.string().optional().describe('Wallet ID. Auto-resolved for single-wallet sessions.'),
        },
        async (args) => {
          const walletId = args.wallet_id || 'default';
          const params = new URLSearchParams();
          if (args.venue !== undefined) params.set('venue', args.venue);
          if (args.status !== undefined) params.set('status', args.status);
          if (args.limit !== undefined) params.set('limit', String(args.limit));
          if (args.offset !== undefined) params.set('offset', String(args.offset));
          const qs = params.toString();
          const result = await apiClient.get(`/v1/wallets/${walletId}/actions${qs ? `?${qs}` : ''}`);
          return toToolResult(result);
        },
      );
    }
  • Zod schema for tool input parameters: venue (optional string), status (optional string), limit (optional number), offset (optional number), wallet_id (optional string).
    {
      venue: z.string().optional().describe('Filter by venue name (e.g. polymarket, hyperliquid)'),
      status: z.string().optional().describe('Filter by status (e.g. PENDING, FILLED, CANCELED, EXPIRED)'),
      limit: z.number().optional().describe('Maximum number of results to return'),
      offset: z.number().optional().describe('Pagination offset'),
      wallet_id: z.string().optional().describe('Wallet ID. Auto-resolved for single-wallet sessions.'),
    },
  • Registration call: registerListOffchainActions(server, apiClient, walletContext) is invoked inside createMcpServer to wire the tool into the MCP server.
    registerListOffchainActions(server, apiClient, walletContext);
  • TypeScript interface ListOffchainActionsParams defining the shape of input parameters (walletId, venue?, status?, limit?, offset?) for the SDK's list-offchain-actions functionality.
    export interface ListOffchainActionsParams {
      walletId: string;
      venue?: string;
      status?: string;
      limit?: number;
      offset?: number;
    }
  • TypeScript interface OffchainActionsListResponse defining the response shape with actions array (OffchainActionItem[]), total, limit, and offset fields.
    export interface OffchainActionsListResponse {
      actions: OffchainActionItem[];
      total: number;
      limit: number;
      offset: number;
    }
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the tool lists history with filtering and pagination, but fails to disclose return format, sorting, error behavior, or any side effects. This is insufficient for a mutation-free read operation.

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 a single 12-word sentence that is perfectly concise and front-loads the core purpose. Every word earns its place.

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 output schema, the description should hint at return value structure, but it does not. However, the tool is a simple list operation with pagination, so the missing information is less critical. It is adequate but could be more complete.

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 baseline is 3. The description adds context by mentioning venue/status filter and pagination, aligning with parameters. It also clarifies action types (signedData/signedHttp) beyond the schema, but does not significantly enhance parameter understanding.

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 tool lists off-chain action history, specifies the action types (signedData/signedHttp), and mentions filtering by venue/status with pagination. This differentiates it from sibling list tools like list_transactions (on-chain) and list_incoming_transactions.

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

Usage Guidelines3/5

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

The description implies usage for retrieving off-chain actions with filtering, but does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites. The context is somewhat clear but lacks explicit guidance.

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/minhoyoo-iotrust/WAIaaS'

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