Skip to main content
Glama
token-metrics

Token Metrics MCP Server

Official

get_tokens_trading_signal

Generate AI-driven trading signals for cryptocurrencies, identifying long and short positions based on token IDs, symbols, dates, market conditions, and technical indicators. Access actionable insights for informed crypto trading decisions.

Instructions

Fetch token(s) AI generated trading signals for long and short positions for a specific date or date range from Token Metrics API.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNoComma Separated category name. Example: yield farming,defi
endDateNoEnd Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-10
exchangeNoComma Separated exchange name. Example: binance,gate
fdvNoMinimum fully diluted valuation in $ (USD) of the token. Example: 100
limitNoLimit the number of results returned. Default is 50. Maximum is 100.
marketcapNoMinimum MarketCap in $ (USD) of the token. Example: 100
pageNoEnables pagination and data retrieval control by skipping a specified number of items before fetching data. Page should be a non-negative integer, with 1 indicating the beginning of the dataset.
signalNoThe current signal value of the strategy of the token, between bullish (1), bearish (-1) or no signal (0). Example: 1
startDateNoStart Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-01
symbolNoComma-separated string of token symbols (e.g., 'BTC,ETH,ADA')
token_idNoComma-separated string of token IDs (e.g., '1,2,3')
volumeNoMinimum 24h trading volume in $ (USD) of the token. Example: 100

Implementation Reference

  • The performApiRequest method, which is the core handler logic specific to this tool. It validates the API key, builds query parameters from input, and makes an API request to the '/trading-signals' endpoint.
    protected async performApiRequest(
      input: TokenTradingSignalInput,
    ): Promise<TokenMetricsResponse> {
      this.validateApiKey();
      const params = this.buildParams(input);
    
      return (await this.makeApiRequest(
        "/trading-signals",
        params,
      )) as TokenMetricsResponse;
    }
  • The getToolDefinition method that provides the tool's name, description, and input schema for validation.
    getToolDefinition(): Tool {
      return {
        name: "get_tokens_trading_signal",
        description:
          "Fetch token(s) AI generated trading signals for long and short positions for a specific date or date range from Token Metrics API.",
        inputSchema: {
          type: "object",
          properties: {
            token_id: {
              type: "string",
              description: "Comma-separated string of token IDs (e.g., '1,2,3')",
            },
            startDate: {
              type: "string",
              description:
                "Start Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-01",
            },
            endDate: {
              type: "string",
              description:
                "End Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-10",
            },
            symbol: {
              type: "string",
              description:
                "Comma-separated string of token symbols (e.g., 'BTC,ETH,ADA')",
            },
            category: {
              type: "string",
              description:
                "Comma Separated category name. Example: yield farming,defi",
            },
            exchange: {
              type: "string",
              description: "Comma Separated exchange name. Example: binance,gate",
            },
            marketcap: {
              type: "string",
              description:
                "Minimum MarketCap in $ (USD) of the token. Example: 100",
            },
            fdv: {
              type: "string",
              description:
                "Minimum fully diluted valuation in $ (USD) of the token. Example: 100",
            },
            volume: {
              type: "string",
              description:
                "Minimum 24h trading volume in $ (USD) of the token. Example: 100",
            },
            signal: {
              type: "string",
              description:
                "The current signal value of the strategy of the token, between bullish (1), bearish (-1) or no signal (0). Example: 1",
            },
            limit: {
              type: "number",
              description:
                "Limit the number of results returned. Default is 50. Maximum is 100.",
            },
            page: {
              type: "number",
              description:
                "Enables pagination and data retrieval control by skipping a specified number of items before fetching data. Page should be a non-negative integer, with 1 indicating the beginning of the dataset.",
            },
          },
          required: [],
        },
      } as Tool;
    }
  • Instantiation of the TokenTradingSignalTool class within the AVAILABLE_TOOLS array, registering it for use in the MCP server.
    new TokenTradingSignalTool(),
  • src/tools/index.ts:8-8 (registration)
    Import of the TokenTradingSignalTool class necessary for its registration.
    import { TokenTradingSignalTool } from "./trading-signal.js";
  • The main class implementing the tool, extending BaseApiTool and providing specific overrides.
    export class TokenTradingSignalTool extends BaseApiTool {
      getToolDefinition(): Tool {
        return {
          name: "get_tokens_trading_signal",
          description:
            "Fetch token(s) AI generated trading signals for long and short positions for a specific date or date range from Token Metrics API.",
          inputSchema: {
            type: "object",
            properties: {
              token_id: {
                type: "string",
                description: "Comma-separated string of token IDs (e.g., '1,2,3')",
              },
              startDate: {
                type: "string",
                description:
                  "Start Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-01",
              },
              endDate: {
                type: "string",
                description:
                  "End Date accepts date as a string - YYYY-MM-DD format. Example: 2023-10-10",
              },
              symbol: {
                type: "string",
                description:
                  "Comma-separated string of token symbols (e.g., 'BTC,ETH,ADA')",
              },
              category: {
                type: "string",
                description:
                  "Comma Separated category name. Example: yield farming,defi",
              },
              exchange: {
                type: "string",
                description: "Comma Separated exchange name. Example: binance,gate",
              },
              marketcap: {
                type: "string",
                description:
                  "Minimum MarketCap in $ (USD) of the token. Example: 100",
              },
              fdv: {
                type: "string",
                description:
                  "Minimum fully diluted valuation in $ (USD) of the token. Example: 100",
              },
              volume: {
                type: "string",
                description:
                  "Minimum 24h trading volume in $ (USD) of the token. Example: 100",
              },
              signal: {
                type: "string",
                description:
                  "The current signal value of the strategy of the token, between bullish (1), bearish (-1) or no signal (0). Example: 1",
              },
              limit: {
                type: "number",
                description:
                  "Limit the number of results returned. Default is 50. Maximum is 100.",
              },
              page: {
                type: "number",
                description:
                  "Enables pagination and data retrieval control by skipping a specified number of items before fetching data. Page should be a non-negative integer, with 1 indicating the beginning of the dataset.",
              },
            },
            required: [],
          },
        } as Tool;
      }
    
      protected async performApiRequest(
        input: TokenTradingSignalInput,
      ): Promise<TokenMetricsResponse> {
        this.validateApiKey();
        const params = this.buildParams(input);
    
        return (await this.makeApiRequest(
          "/trading-signals",
          params,
        )) as TokenMetricsResponse;
      }
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't disclose whether this is a read-only operation, rate limits, authentication requirements, error handling, or response format. The phrase 'Fetch' implies a safe read operation, but this isn't explicitly confirmed. More context on API constraints or data freshness would help.

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 that front-loads the core purpose without unnecessary words. Every part earns its place: verb, resource, key attributes (long/short positions, date range), and data source. No redundancy or fluff.

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?

For a tool with 12 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain the return structure (e.g., list of signals with fields), pagination behavior (implied by page/limit but not described), or how filters combine. The agent lacks context to interpret results or handle edge cases.

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 parameters are well-documented in the schema itself. The description adds no additional parameter semantics beyond implying date-range filtering. It doesn't explain relationships between parameters (e.g., how symbol interacts with category) or provide examples of combined usage. Baseline 3 is appropriate given the schema does the heavy lifting.

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 action ('Fetch'), resource ('token(s) AI generated trading signals'), and scope ('for long and short positions for a specific date or date range from Token Metrics API'). It distinguishes from siblings like get_tokens_price or get_tokens_data by specifying trading signals, but doesn't explicitly differentiate from get_tokens_ai_report or get_tokens_quant_metrics which might overlap.

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 like get_tokens_ai_report or get_tokens_quant_metrics. It mentions the source (Token Metrics API) but doesn't explain use cases, prerequisites, or exclusions. The agent must infer usage from the tool name and parameters alone.

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

Related 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/token-metrics/mcp'

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