Skip to main content
Glama
cexll
by cexll

fetch-chunk

Retrieves cached data chunks from partial responses in the Codex MCP Server, enabling sequential access to large code analysis results for AI-assisted programming tasks.

Instructions

Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cacheKeyYesThe cache key provided in the initial changeMode response
chunkIndexYesWhich chunk to retrieve (1-based index)

Implementation Reference

  • The main execute function that handles the tool invocation: parses args, fetches chunks from cache using getChunks, validates chunkIndex, formats the response with formatChangeModeResponse, adds summary if first chunk, and returns formatted output or error messages.
      execute: async (args: any, onProgress?: (newOutput: string) => void): Promise<string> => {
        const { cacheKey, chunkIndex } = args;
    
        Logger.toolInvocation('fetch-chunk', args);
        Logger.debug(`Fetching chunk ${chunkIndex} with cache key: ${cacheKey}`);
    
        // Retrieve cached chunks
        const chunks = getChunks(cacheKey);
    
        if (!chunks) {
          return `❌ Cache miss: No chunks found for cache key "${cacheKey}". 
    
      Possible reasons:
      1. The cache key is incorrect. Did you run ask-codex with changeMode enabled?
      2. The cache has expired (10 minute TTL)
      3. The MCP server was restarted and the file-based cache was cleared
    
    Please re-run the original changeMode request to regenerate the chunks.`;
        }
    
        // Validate chunk index
        if (chunkIndex < 1 || chunkIndex > chunks.length) {
          return `❌ Invalid chunk index: ${chunkIndex}
    
    Available chunks: 1 to ${chunks.length}
    You requested: ${chunkIndex}
    
    Please use a valid chunk index.`;
        }
    
        // Get the requested chunk
        const chunk = chunks[chunkIndex - 1];
    
        // Format the response
        let result = formatChangeModeResponse(chunk.edits, {
          current: chunkIndex,
          total: chunks.length,
          cacheKey,
        });
    
        // Add summary for first chunk
        if (chunkIndex === 1 && chunks.length > 1) {
          const allEdits = chunks.flatMap(c => c.edits);
          result = summarizeChangeModeEdits(allEdits, true) + '\n\n' + result;
        }
    
        Logger.debug(
          `Returning chunk ${chunkIndex} of ${chunks.length} with ${chunk.edits.length} edits`
        );
    
        return result;
      },
  • Zod input schema defining the required parameters: cacheKey (string) and chunkIndex (number >=1).
    const inputSchema = z.object({
      cacheKey: z.string().describe('The cache key provided in the initial changeMode response'),
      chunkIndex: z.number().min(1).describe('Which chunk to retrieve (1-based index)'),
    });
  • The fetchChunkTool is imported (line 8) and registered by pushing it to the toolRegistry array alongside other tools.
    toolRegistry.push(
      askCodexTool,
      batchCodexTool,
      // reviewCodexTool,
      pingTool,
      helpTool,
      versionTool,
      brainstormTool,
      fetchChunkTool,
      timeoutTestTool
    );

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/cexll/codex-mcp-server'

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