Skip to main content
Glama

get-docs

Retrieve complete documentation content for specific routes, including code examples, detailed explanations, and API references, after identifying relevant documentation through search.

Instructions

Retrieve the full documentation content for a specific route. After finding relevant documentation with search-docs, use this tool to get the complete markdown content including code examples, detailed explanations, and API references.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
routeYes

Implementation Reference

  • Handler function for the 'get-docs' tool. Takes a route parameter, calls the /content API endpoint, and returns markdown-formatted content blocks with the JSON data and full documentation text, plus structured content.
    async ({route}) => {
        const data = await callApi<ContentResponse>('/content', {
            searchParams: {
                route
            }
        });
    
        return {
            content: [
                {
                    type: 'text' as const,
                    text: formatJsonBlock(`Content for ${route}`, data)
                },
                {
                    type: 'text' as const,
                    text: data.content
                }
            ],
            structuredContent: data
        };
    }
  • Zod input schema for 'get-docs' tool, validating the 'route' parameter as a string starting with '/'.
    inputSchema: {
        route: z.string().regex(/^\/.*/, 'route must start with /')
    }
  • src/index.ts:266-296 (registration)
    Registration of the 'get-docs' tool with McpServer, including title, description, input schema, and inline handler function.
    server.registerTool(
        'get-docs',
        {
            title: 'Get PDFDancer documentation',
            description: 'Retrieve the full documentation content for a specific route. After finding relevant documentation with search-docs, use this tool to get the complete markdown content including code examples, detailed explanations, and API references.',
            inputSchema: {
                route: z.string().regex(/^\/.*/, 'route must start with /')
            }
        },
        async ({route}) => {
            const data = await callApi<ContentResponse>('/content', {
                searchParams: {
                    route
                }
            });
    
            return {
                content: [
                    {
                        type: 'text' as const,
                        text: formatJsonBlock(`Content for ${route}`, data)
                    },
                    {
                        type: 'text' as const,
                        text: data.content
                    }
                ],
                structuredContent: data
            };
        }
    );
  • Helper function 'callApi' used by 'get-docs' handler to make HTTP GET requests to the documentation API endpoints, construct URLs, handle parameters, fetch, parse JSON, and throw errors on failure.
    async function callApi<T>(path: string, options: ApiRequestOptions = {}): Promise<T> {
        const url = new URL(path, apiBase);
        if (options.searchParams) {
            Object.entries(options.searchParams).forEach(([key, value]) => {
                if (value !== undefined && value !== null && value !== '') {
                    url.searchParams.set(key, String(value));
                }
            });
        }
    
        const method = options.method ?? 'GET';
        const init: RequestInit = {
            method,
            headers: {
                Accept: 'application/json',
                ...(options.body ? {'Content-Type': 'application/json'} : {})
            }
        };
    
        if (options.body && method === 'POST') {
            init.body = JSON.stringify(options.body);
        }
    
        const response = await fetch(url, init);
        const text = await response.text();
    
        if (!response.ok) {
            throw new Error(
                `Request to ${url.toString()} failed with status ${response.status}: ${
                    text || response.statusText
                }`
            );
        }
    
        if (!text) {
            return undefined as T;
        }
    
        try {
            return JSON.parse(text) as T;
        } catch (error) {
            throw new Error(`Failed to parse JSON response from ${url.toString()}: ${error}`);
        }
    }
  • Helper function 'formatJsonBlock' formats JSON payloads as markdown code blocks, used in the response content of 'get-docs'.
    function formatJsonBlock(title: string, payload: unknown): string {
        return `${title}\n\`\`\`json\n${JSON.stringify(payload, null, 2)}\n\`\`\``;
    }
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/MenschMachine/pdfdancer-mcp'

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