Skip to main content
Glama
maven81g

TradeStation MCP Server

by maven81g

getPositions

Retrieve current trading positions with profit and loss data for account management and portfolio tracking.

Instructions

Get current positions with P&L

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
accountIdNoAccount ID (optional, uses TRADESTATION_ACCOUNT_ID from env if not provided)

Implementation Reference

  • The handler function for the 'getPositions' tool. It retrieves current positions and P&L data for a specified TradeStation brokerage account by making an authenticated API request to `/brokerage/accounts/{accountId}/positions`.
      async (args) => {
        try {
          const accountId = args.accountId || TS_ACCOUNT_ID;
    
          if (!accountId) {
            throw new Error('Account ID is required. Either provide accountId parameter or set TRADESTATION_ACCOUNT_ID in .env file.');
          }
    
          const positions = await makeAuthenticatedRequest(
            `/brokerage/accounts/${encodeURIComponent(accountId)}/positions`
          );
    
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(positions, null, 2)
              }
            ]
          };
        } catch (error: unknown) {
          return {
            content: [
              {
                type: "text",
                text: `Failed to fetch positions: ${error instanceof Error ? error.message : 'Unknown error'}`
              }
            ],
            isError: true
          };
        }
      }
    );
  • Zod schema defining the input parameters for the 'getPositions' tool, with an optional accountId.
    const positionsSchema = {
      accountId: z.string().optional().describe('Account ID (optional, uses TRADESTATION_ACCOUNT_ID from env if not provided)')
    };
  • src/index.ts:509-512 (registration)
    Registration of the 'getPositions' tool on the MCP server using server.tool() with name, description, schema, and handler function.
    server.tool(
      "getPositions",
      "Get current positions with P&L",
      positionsSchema,
  • Shared helper function used by the getPositions handler to make authenticated requests to the TradeStation API, including token refresh logic.
    async function makeAuthenticatedRequest(
      endpoint: string,
      method: AxiosRequestConfig['method'] = 'GET',
      data: any = null
    ): Promise<any> {
      const userTokens = tokenStore.get(DEFAULT_USER);
    
      if (!userTokens) {
        throw new Error('User not authenticated. Please set TRADESTATION_REFRESH_TOKEN in .env file.');
      }
    
      // Check if token is expired or about to expire (within 60 seconds)
      if (userTokens.expiresAt < Date.now() + 60000) {
        // Refresh the token
        const newTokens = await refreshToken(userTokens.refreshToken);
        tokenStore.set(DEFAULT_USER, newTokens);
      }
    
      try {
        const options: AxiosRequestConfig = {
          method,
          url: `${TS_API_BASE}${endpoint}`,
          headers: {
            'Authorization': `Bearer ${tokenStore.get(DEFAULT_USER)?.accessToken}`,
            'Content-Type': 'application/json',
            'Accept': 'application/json'
          },
          timeout: 60000
        };
    
        if (data && (method === 'POST' || method === 'PUT' || method === 'PATCH')) {
          options.data = data;
        }
    
        const response = await axios(options);
        return response.data;
      } catch (error: unknown) {
        if (error instanceof AxiosError) {
          const errorMessage = error.response?.data?.Message || error.response?.data?.message || error.message;
          const statusCode = error.response?.status;
          console.error(`API request error [${statusCode}]: ${errorMessage}`);
          console.error('Endpoint:', endpoint);
          throw new Error(`API Error (${statusCode}): ${errorMessage}`);
        } else if (error instanceof Error) {
          console.error('API request error:', error.message);
          throw error;
        } else {
          console.error('Unknown API request error:', error);
          throw new Error('Unknown API request error');
        }
      }
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'Get current positions with P&L', which implies a read-only operation, but doesn't specify data freshness (e.g., real-time vs. cached), authentication needs, rate limits, or error handling. For a financial tool with no annotation coverage, this is a significant gap in transparency.

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, efficient sentence with no wasted words, clearly stating the tool's purpose. It's appropriately sized and front-loaded, making it easy to understand at a glance without unnecessary elaboration.

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

Completeness2/5

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

Given the complexity of financial data retrieval and the lack of annotations and output schema, the description is insufficient. It doesn't explain what 'P&L' entails (e.g., unrealized vs. realized), the format of returned positions, or any prerequisites like account setup. For a tool in this context, more detail is needed to ensure proper usage.

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?

The input schema has 100% description coverage, with the single parameter 'accountId' well-documented in the schema. The description doesn't add any parameter-specific details beyond what the schema provides, such as clarifying what 'P&L' includes or default behaviors. Baseline 3 is appropriate since the schema handles the parameter documentation adequately.

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

Purpose4/5

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

The description clearly states the verb 'Get' and the resource 'current positions with P&L', making the purpose evident. However, it doesn't distinguish this tool from potential siblings like 'getBalances' or 'getOrders', which might also retrieve financial data, leaving room for ambiguity in a trading context.

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. In a server with multiple financial tools like 'getBalances' or 'getOrders', there's no indication of whether this is for real-time positions, historical data, or specific account types, making it unclear when this is the appropriate choice.

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/maven81g/tradestation_mcp'

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