Skip to main content
Glama
pinzonjulian

Stimulus Docs MCP Server

by pinzonjulian

reference-typescript

Learn to integrate TypeScript with Stimulus by implementing type definitions, strongly typed targets, values, and outlets following established best practices.

Instructions

TypeScript integration guide - covers type definitions, strongly typed targets/values/outlets, and best practices for using Stimulus with TypeScript

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • src/index.ts:17-45 (registration)
    Dynamically registers the 'reference-typescript' MCP tool (and all others) by iterating over docFiles config, calling server.tool with the tool name, description, and a handler that reads the corresponding markdown file.
    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}`
                }
              ]
            };
          }
        }
      );
    });
  • The handler function executed when the 'reference-typescript' tool is called. Reads the markdown content from 'reference/using_typescript.md' and returns it as MCP content block, with fallback error message.
    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}`
            }
          ]
        };
      }
    }
  • Core helper function that implements file reading logic: checks cache first, then fetches from GitHub (with caching), falls back to local files. Called by the tool handler with filename 'reference/using_typescript.md'.
    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})`);
        }
      }
    }
  • Configuration entry defining the 'reference-typescript' tool: specifies the source file path, tool name, and description used in registration.
    {
      folder: 'reference', file: 'using_typescript.md',
      name: 'reference-typescript',
      description: 'TypeScript integration guide - covers type definitions, strongly typed targets/values/outlets, and best practices for using Stimulus with TypeScript'
    },
  • Supporting utility for fetching markdown content directly from GitHub raw URL and caching it locally, used by readMarkdownFile.
    export async function fetchFromGitHub(filename: string, cacheKey?: string): Promise<string> {
      const githubUrl = `${GITHUB_RAW_BASE_URL}/${filename}`;
      const response = await fetch(githubUrl);
      
      if (!response.ok) {
        throw new Error(`GitHub fetch failed: ${response.status} ${response.statusText}`);
      }
      
      const content = await response.text();
      
      // Cache the content with cache key if available
      if (cacheKey) {
        try {
          const cacheFolder = path.resolve(__dirname, "../cache");
          const cachedFilePath = path.join(cacheFolder, cacheKey, filename);
          await fs.promises.mkdir(path.dirname(cachedFilePath), { recursive: true });
          await fs.promises.writeFile(cachedFilePath, content, "utf-8");
          console.error(`Cached GitHub content for ${cacheKey}: ${filename}`);
        } catch (cacheError) {
          console.error(`Failed to cache content: ${cacheError}`);
        }
      }
      
      return content;
    }
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 describes the content ('integration guide') but doesn't specify behavioral traits such as whether it's read-only, if it requires authentication, how it presents information (e.g., static documentation vs. interactive), or any rate limits. The description is functional but lacks operational context needed for an AI agent to understand how to interact with it effectively.

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 key information ('TypeScript integration guide') and lists specific coverage areas. There's no wasted text, and it's appropriately sized for a tool with no parameters. However, it could be slightly more structured by explicitly stating the tool's action (e.g., 'Provides a guide for...').

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 the tool has no parameters, no annotations, and no output schema, the description is moderately complete. It explains what the tool covers (TypeScript integration for Stimulus) but lacks details on the output format (e.g., whether it returns text, HTML, or structured data) and behavioral context. For a guide tool, this is adequate but leaves gaps in understanding how the tool behaves when invoked.

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 input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's purpose. This meets the baseline of 4 for tools with no parameters, as it avoids unnecessary details and aligns with the schema.

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 tool's purpose as providing a TypeScript integration guide covering specific technical areas (type definitions, strongly typed targets/values/outlets, and best practices for Stimulus with TypeScript). It distinguishes itself from siblings by focusing on TypeScript integration rather than general handbook topics or other reference areas like actions or controllers. However, it doesn't specify the exact verb (e.g., 'read', 'generate', 'explain') for what the tool does.

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. It doesn't mention prerequisites (e.g., needing TypeScript knowledge), exclusions (e.g., not for JavaScript users), or direct comparisons to sibling tools like 'reference-actions' or 'reference-controllers'. The context is implied as TypeScript-related Stimulus development, but explicit usage instructions are absent.

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/stimulus-docs-mcp-server'

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