Skip to main content
Glama
pinzonjulian

Turbo Docs MCP Server

by pinzonjulian

handbook-building

Build Turbo applications by handling scripts, bundling JavaScript, implementing caching strategies, installing Stimulus behavior, making transformations idempotent, and persisting elements across page loads.

Instructions

Building Turbo applications - covers script handling, JavaScript bundling, caching strategies, installing behavior with Stimulus, making transformations idempotent, and persisting elements across page loads

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Handler function for the 'handbook-building' tool (shared across all doc tools). Fetches the markdown content for the specified file using readMarkdownFile and returns it as MCP content block, with error handling.
    async () => {
      try {
        const content = await readMarkdownFile(path.join(folder, file));
        return {
          content: [
            {
              type: "text",
              text: content
            }
          ]
        };
      } catch (error) {
        const errorMessage = error instanceof Error ? error.message : String(error);
        return {
          content: [
            {
              type: "text",
              text: `Error reading ${file}: ${errorMessage}`
            }
          ]
        };
      }
    }
  • src/index.ts:17-45 (registration)
    Registers the 'handbook-building' tool by iterating over docFiles from config.ts and calling server.tool with the tool's name, description, and handler function.
    docFiles.forEach(({ folder, file, name, description }) => {
      server.tool(
        name,
        description,
        async () => {
          try {
            const content = await readMarkdownFile(path.join(folder, file));
            return {
              content: [
                {
                  type: "text",
                  text: content
                }
              ]
            };
          } catch (error) {
            const errorMessage = error instanceof Error ? error.message : String(error);
            return {
              content: [
                {
                  type: "text",
                  text: `Error reading ${file}: ${errorMessage}`
                }
              ]
            };
          }
        }
      );
    });
  • Schema/configuration defining the 'handbook-building' tool: its name, description, source folder, and filename.
    {
      folder: 'handbook',
      file: '07_building.md',
      name: 'handbook-building',
      description: 'Building Turbo applications - covers script handling, JavaScript bundling, caching strategies, installing behavior with Stimulus, making transformations idempotent, and persisting elements across page loads'
    },
  • Helper function called by the tool handler to read the markdown file content, implementing caching, GitHub API fetching, and local fallback.
    export async function readMarkdownFile(filename: string): Promise<string> {
      const filePath = path.join(docsFolder, filename);
      if (!filePath.startsWith(docsFolder)) {
        throw new Error("Invalid file path");
      }
      
      // Get current commit info if we don't have it yet
      if (!mainBranchInfo) {
        try {
          const commitInfo = await fetchMainBranchInformation();
          const cacheKey = `${commitInfo.sha.substring(0, 7)}-${commitInfo.timestamp}`;
          mainBranchInfo = {
            ...commitInfo,
            cacheKey
          };
        } catch (shaError) {
          console.error('Failed to get GitHub commit info, falling back to direct fetch');
        }
      }
      
      // Try to read from cache first if we have commit info
      if (mainBranchInfo) {
        const cachedFilePath = path.join(cacheFolder, mainBranchInfo.cacheKey, filename);
        try {
          const content = await fs.promises.readFile(cachedFilePath, "utf-8");
          console.error(`Using cached content for ${mainBranchInfo.cacheKey}: ${filename}`);
          return content;
        } catch (cacheError) {
          // Cache miss, continue to fetch from GitHub
        }
      }
      
      // Fetch from GitHub
      try {
        return await fetchFromGitHub(filename, mainBranchInfo?.cacheKey);
      } catch (githubError) {
        console.error(`GitHub fetch failed: ${githubError}, attempting to read from local files...`);
        
        // Fallback: read from local files
        try {
          return await fs.promises.readFile(filePath, "utf-8");
        } catch (localError) {
          const githubErrorMessage = githubError instanceof Error ? githubError.message : String(githubError);
          const localErrorMessage = localError instanceof Error ? localError.message : String(localError);
          throw new Error(`Failed to read file from GitHub (${githubErrorMessage}) and locally (${localErrorMessage})`);
        }
      }
    }
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 offers minimal behavioral insight. It lists topics covered but doesn't describe what the tool actually does - whether it's informational, instructional, or functional. There's no indication of output format, interaction patterns, or what happens when invoked.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single run-on sentence listing topics without clear organization. While it's brief, the comma-separated list format makes it difficult to parse. It could be more structured by grouping related concepts or using bullet points for better readability.

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 no parameters, no annotations, and no output schema, the description is insufficient. It lists topics but doesn't explain what the tool produces or how it helps the agent. Given the complexity implied by the topic list (JavaScript bundling, caching strategies, etc.), more context about the tool's function is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, which is correct for a parameterless tool.

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

Purpose2/5

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

The description lists topics covered rather than stating a specific action. 'Building Turbo applications' is vague about what the tool actually does - it doesn't specify whether it's a guide, a builder, or a reference. While it distinguishes from siblings by listing specific Turbo-related topics, it's more of a content summary than a clear purpose statement.

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?

No guidance on when to use this tool versus the 11 sibling tools is provided. The description doesn't indicate whether this is for learning, reference, or implementation. With multiple handbook-* and reference-* siblings, the lack of comparative guidance leaves the agent guessing about appropriate use cases.

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/pinzonjulian/turbo-docs-mcp-server'

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