Skip to main content
Glama
CoinStatsHQ

CoinStats MCP Server

Official

get-coin-chart-by-id

Retrieve cryptocurrency chart data by specifying a coin identifier and time period to analyze price trends and historical performance.

Instructions

Get chart data for a specific cryptocurrency based on its unique identifier, specifying different time ranges.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinIdYesThe identifier of coin, which you received from /coins call response.
periodYesTime period for chart data

Implementation Reference

  • Generic MCP tool handler registered for 'get-coin-chart-by-id'. For API tools, constructs the API call using config.endpoint ('/coins/{coinId}/charts'), method ('GET'), and passes parameters to universalApiHandler which handles path replacement and query params.
    server.tool(config.name, config.description, config.parameters, async (params: Record<string, any>) => {
        // Handle local operations
        if (config.isLocal) {
            // Handle specific local tools
            if (config.name === 'save-share-token') {
                await saveToCache('shareToken', params.shareToken);
                return {
                    content: [
                        {
                            type: 'text',
                            text: 'Share token saved successfully',
                        },
                    ],
                };
            }
    
            if (config.name === 'get-share-token') {
                const shareToken = await getFromCache('shareToken');
    
                return {
                    content: [
                        {
                            type: 'text',
                            text: shareToken ? shareToken : 'No share token found in cache',
                            isError: !shareToken,
                        },
                    ],
                };
            }
            // Future local tools can be added here
    
            // Default response for unhandled local tools
            return {
                content: [
                    {
                        type: 'text',
                        text: 'Operation completed',
                    },
                ],
            };
        }
    
        // Handle API operations
        const basePath = config.basePath || COINSTATS_API_BASE;
        const method = config.method || 'GET';
    
        // Methods that typically have a request body
        const bodyMethods = ['POST', 'PUT', 'PATCH', 'DELETE'];
    
        // For GET/DELETE requests, all params go in the URL
        // For POST/PUT/PATCH, send params as the body
        if (bodyMethods.includes(method.toUpperCase())) {
            return universalApiHandler(basePath, config.endpoint, method, {}, params);
        } else {
            return universalApiHandler(basePath, config.endpoint, method, params);
        }
    });
  • Tool schema definition: name, description, endpoint, method, and Zod-parameter schema for input validation (coinId: string, period: enum).
    {
        name: 'get-coin-chart-by-id',
        description: 'Get chart data for a specific cryptocurrency based on its unique identifier, specifying different time ranges.',
        endpoint: '/coins/{coinId}/charts',
        method: 'GET',
        parameters: {
            coinId: z.string().describe('The identifier of coin, which you received from /coins call response.'),
            period: z.enum(['all', '24h', '1w', '1m', '3m', '6m', '1y']).describe('Time period for chart data'),
        },
    },
  • src/index.ts:17-18 (registration)
    Registers the MCP server tools by calling registerTools with allToolConfigs, which includes 'get-coin-chart-by-id'.
    // Register all tools from configurations
    registerTools(server, allToolConfigs);
  • Helper function called by the tool handler: replaces path params like {coinId}, adds remaining params as query, makes authenticated fetch to CoinStats API using makeRequestCsApi, returns JSON string in MCP format or error.
    export async function universalApiHandler<T>(
        basePath: string,
        endpoint: string,
        method: string = 'GET',
        params: Record<string, any> = {},
        body?: any
    ): Promise<{
        content: Array<{ type: 'text'; text: string; isError?: boolean }>;
    }> {
        try {
            // Handle path parameters - replace {paramName} in endpoint with actual values
            let processedEndpoint = endpoint;
            let processedParams = { ...params };
    
            // Find all path parameters in the endpoint (e.g., {coinId}, {id}, {type})
            const pathParamMatches = endpoint.match(/\{([^}]+)\}/g);
    
            if (pathParamMatches) {
                for (const match of pathParamMatches) {
                    const paramName = match.slice(1, -1); // Remove { and }
    
                    if (processedParams[paramName] !== undefined) {
                        // Replace the placeholder with the actual value
                        processedEndpoint = processedEndpoint.replace(match, processedParams[paramName]);
                        // Remove the parameter from query params since it's now part of the path
                        delete processedParams[paramName];
                    } else {
                        throw new Error(`Required path parameter '${paramName}' is missing`);
                    }
                }
            }
    
            // MCP clients might not support '~' in parameter names, so we replace '-' with '~' specifically for the /coins endpoint before making the request.
            if (endpoint === '/coins') {
                processedParams = Object.entries(processedParams).reduce((acc, [key, value]) => {
                    acc[key.replace(/-/g, '~')] = value;
                    return acc;
                }, {} as Record<string, any>);
            }
    
            const url = `${basePath}${processedEndpoint}`;
            const data = await makeRequestCsApi<T>(url, method, processedParams, body);
    
            if (!data) {
                return {
                    content: [{ type: 'text', text: 'Something went wrong', isError: true }],
                };
            }
    
            return {
                content: [
                    {
                        type: 'text',
                        text: JSON.stringify(data),
                    },
                ],
            };
        } catch (error) {
            return {
                content: [{ type: 'text', text: `Error: ${error}`, isError: true }],
            };
        }
    }
  • Core HTTP request helper: performs fetch to CoinStats API with API key header, handles query params and body, returns parsed JSON or null on error.
    export async function makeRequestCsApi<T>(url: string, method: string = 'GET', params: Record<string, any> = {}, body?: any): Promise<T | null> {
        const headers = {
            'X-API-KEY': COINSTATS_API_KEY,
            'Content-Type': 'application/json',
        };
    
        try {
            // Build request options
            const options: RequestInit = { method, headers };
    
            // Add body for non-GET requests if provided
            if (method !== 'GET' && body) {
                options.body = JSON.stringify(body);
            }
    
            // Add query params for all requests
            const queryParams = new URLSearchParams(params);
            const queryString = queryParams.toString();
            const urlWithParams = queryString ? `${url}?${queryString}` : url;
    
            const response = await fetch(urlWithParams, options);
            if (!response.ok) {
                throw new Error(`HTTP error! status: ${response.status}`);
            }
            return (await response.json()) as T;
        } catch (error) {
            return null;
        }
    }
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states it 'gets' data, implying a read-only operation, but doesn't clarify authentication needs, rate limits, response format, or error handling. For a tool with no annotation coverage, this leaves significant behavioral gaps.

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?

The description is a single, efficient sentence that front-loads the core purpose. It avoids unnecessary words and directly addresses what the tool does. However, it could be slightly more structured by separating the purpose from the parameter 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?

Given no annotations and no output schema, the description is moderately complete for a simple read operation. It covers the purpose and hints at parameters, but lacks details on authentication, response format, or error handling. For a tool with 2 parameters and 100% schema coverage, it's adequate but leaves room for improvement in behavioral context.

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 both parameters. The description adds minimal value beyond the schema by mentioning 'time ranges' which aligns with the 'period' parameter, but doesn't provide additional context like format examples or usage tips. Baseline 3 is appropriate when 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 verb 'Get' and resource 'chart data for a specific cryptocurrency', making the purpose evident. It distinguishes from siblings like 'get-coin-by-id' by specifying chart data retrieval rather than general coin information. However, it doesn't explicitly differentiate from 'get-portfolio-chart' which might serve a similar charting function for portfolios.

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-coin-by-id' for general data or 'get-portfolio-chart' for portfolio-specific charts. It mentions 'specifying different time ranges' but doesn't explain when to choose this over other charting or data retrieval tools in the sibling list.

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/CoinStatsHQ/coinstats-mcp'

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