Skip to main content
Glama

replace_content

Search and replace text or regex patterns in files across specified paths. Perform multiple operations at once, with options to ignore case or use regex.

Instructions

Replace content within files across multiple specified paths.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationsYesAn array of search/replace operations to apply to each file.
pathsYesAn array of relative file paths to perform replacements on.

Implementation Reference

  • Core internal handler function that orchestrates argument parsing, file processing, and response formatting for the replace_content tool.
    export const handleReplaceContentInternal = async (
      args: unknown,
      deps: ReplaceContentDeps,
    ): Promise<McpToolResponse> => {
      // Specify output type
      const { paths: relativePaths, operations } = parseAndValidateArgs(args);
    
      const finalResults = await processAllFilesReplacement(relativePaths, operations, deps);
    
      // Return results in McpToolResponse format
      return {
        success: true,
        data: {
          results: finalResults,
        },
        content: [
          {
            type: 'text',
            text: JSON.stringify({ results: finalResults }, undefined, 2),
          },
        ],
      };
    };
  • Input schemas defining the structure for replace_content tool arguments: ReplaceOperationSchema and ReplaceContentArgsSchema.
    export const ReplaceOperationSchema = z
      .object({
        search: z.string().describe('Text or regex pattern to search for.'),
        replace: z.string().describe('Text to replace matches with.'),
        use_regex: z.boolean().optional().default(false).describe('Treat search as regex.'),
        ignore_case: z.boolean().optional().default(false).describe('Ignore case during search.'),
      })
      .strict();
    
    export const ReplaceContentArgsSchema = z
      .object({
        paths: z
          .array(z.string())
          .min(1, { message: 'Paths array cannot be empty' })
          .describe('An array of relative file paths to perform replacements on.'),
        operations: z
          .array(ReplaceOperationSchema)
          .min(1, { message: 'Operations array cannot be empty' })
          .describe('An array of search/replace operations to apply to each file.'),
      })
      .strict();
  • Tool definition for 'replace_content' including name, description, input/output schemas, and handler wrapper that provides dependencies.
    export const replaceContentToolDefinition = {
      name: 'replace_content',
      description: 'Replace content within files across multiple specified paths.',
      inputSchema: ReplaceContentArgsSchema,
      // Define output schema for better type safety and clarity
      outputSchema: z.object({
        results: z.array(
          z.object({
            file: z.string(),
            replacements: z.number().int(),
            modified: z.boolean(),
            error: z.string().optional(),
          }),
        ),
      }),
      // Use locally defined McpResponse type with proper request type
      handler: async (args: unknown): Promise<McpToolResponse> => {
        // Validate input using schema first
        const validatedArgs = ReplaceContentArgsSchema.parse(args);
        // Production handler provides real dependencies
        const productionDeps: ReplaceContentDeps = {
          readFile: fs.readFile,
          writeFile: fs.writeFile,
          stat: fs.stat,
          resolvePath: resolvePath,
        };
        return handleReplaceContentInternal(validatedArgs, productionDeps);
      },
    };
  • Import and registration of replaceContentToolDefinition into the central allToolDefinitions array used for MCP tool exposure.
    import { replaceContentToolDefinition } from './replace-content.js';
    import { handleApplyDiff } from './apply-diff.js';
    import { applyDiffInputSchema, ApplyDiffOutput } from '../schemas/apply-diff-schema.js';
    import fs from 'node:fs';
    import path from 'node:path';
    
    // Define the structure for a tool definition (used internally and for index.ts)
    import type { ZodType } from 'zod';
    import type { McpToolResponse } from '../types/mcp-types.js';
    
    // Define local interfaces based on usage observed in handlers
    // Define the structure for a tool definition
    // Matches the structure in individual tool files like applyDiff.ts
    export interface ToolDefinition<TInput = unknown, TOutput = unknown> {
      name: string;
      description: string;
      inputSchema: ZodType<TInput>;
      outputSchema?: ZodType<TOutput>;
      handler: (args: TInput) => Promise<McpToolResponse>; // Changed _args to args
    }
    
    // Helper type to extract input type from a tool definition
    export type ToolInput<T extends ToolDefinition> =
      T extends ToolDefinition<infer I, unknown> ? I : never;
    
    // Define a more specific type for our tool definitions to avoid naming conflicts
    type HandlerToolDefinition = {
      name: string;
      description: string;
      inputSchema: ZodType<unknown>;
      outputSchema?: ZodType<unknown>;
      handler: (args: unknown) => Promise<{ content: Array<{ type: 'text'; text: string }> }>;
    };
    
    // Aggregate all tool definitions into a single array
    // Use our more specific type to avoid naming conflicts
    export const allToolDefinitions: HandlerToolDefinition[] = [
      listFilesToolDefinition,
      statItemsToolDefinition,
      readContentToolDefinition,
      writeContentToolDefinition,
      deleteItemsToolDefinition,
      createDirectoriesToolDefinition,
      chmodItemsToolDefinition,
      chownItemsToolDefinition,
      moveItemsToolDefinition,
      copyItemsToolDefinition,
      searchFilesToolDefinition,
      replaceContentToolDefinition,
  • Key helper function that processes replacements for a single file, including reading content, applying operations, writing changes, and error handling.
    async function processSingleFileReplacement(
      relativePath: string,
      operations: ReplaceOperation[],
      deps: ReplaceContentDeps,
    ): Promise<ReplaceResult> {
      const pathOutput = relativePath.replaceAll('\\', '/');
      let targetPath = '';
      let originalContent = '';
      let fileContent = '';
      let totalReplacements = 0;
      let modified = false;
    
      try {
        targetPath = await deps.resolvePath(relativePath);
        const stats = await deps.stat(targetPath);
        if (!stats.isFile()) {
          // Return specific error if path is not a file
          return {
            file: pathOutput,
            replacements: 0,
            modified: false,
            error: 'Path is not a file',
          };
        }
    
        originalContent = await deps.readFile(targetPath, 'utf8');
        fileContent = originalContent;
    
        for (const op of operations) {
          const { newContent, replacementsMade } = applyReplaceOperation(fileContent, op);
          // Only update content and count if replacements were actually made
          if (replacementsMade > 0 && newContent !== fileContent) {
            fileContent = newContent;
            totalReplacements += replacementsMade; // Accumulate replacements across operations
          }
        }
    
        // Check if content actually changed after all operations
        if (fileContent !== originalContent) {
          modified = true;
          await deps.writeFile(targetPath, fileContent, 'utf8');
        }
    
        return { file: pathOutput, replacements: totalReplacements, modified };
      } catch (error: unknown) {
        // Catch any error during the process (resolve, stat, read, write)
        const fileError = handleReplaceError(error, relativePath);
        return {
          file: pathOutput,
          replacements: totalReplacements, // Return replacements count even on write error
          modified: false,
          error: fileError, // Use the formatted error message
        };
      }
    }
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 states the tool performs replacements but doesn't mention critical behaviors: whether it modifies files in-place, requires write permissions, handles errors, backs up original content, or has rate limits. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core action ('Replace content') and scope ('within files across multiple specified paths'). There is zero waste or redundancy, making it highly concise and well-structured for quick comprehension.

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?

Given this is a mutation tool with no annotations, no output schema, and 2 parameters, the description is incomplete. It lacks information on behavioral traits (e.g., destructive nature, error handling), output format, and usage context. While the schema covers parameters well, the overall context for safe and effective use is insufficient.

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 the 'paths' and 'operations' parameters with their nested properties. The description adds no additional meaning beyond implying batch processing across multiple files, which is already clear from the schema. Baseline 3 is appropriate as the 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 'Replace' and the resource 'content within files across multiple specified paths', which is specific and unambiguous. It distinguishes from siblings like 'write_content' (which creates new content) and 'read_content' (which only reads), though it doesn't explicitly mention these distinctions. The purpose is well-defined but could be more precise about scope.

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 'write_content' for creating new files or 'search_files' for finding content without replacement. It mentions 'multiple specified paths' but doesn't clarify prerequisites, limitations, or typical use cases, leaving the agent to infer usage from the tool name alone.

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

Related 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/SylphxAI/filesystem-mcp'

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