Skip to main content
Glama
A-Niranjan

MCP Filesystem Server

by A-Niranjan

edit_file

Modify text files by replacing specific line sequences with new content, generating a git-style diff to track changes within allowed directories.

Instructions

Make line-based edits to a text file. Each edit replaces exact line sequences with new content. Returns a git-style diff showing the changes made. Only works within allowed directories.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesPath to the file to edit
editsYesList of edit operations to perform
dryRunNoPreview changes using git-style diff format

Implementation Reference

  • The editFile function that executes the core logic of the 'edit_file' tool: validates path, reads file, applies sequential exact-match text replacements preserving indentation, generates unified diff, writes changes if not dry-run.
    export async function editFile(
      args: z.infer<typeof EditFileArgsSchema>,
      config: Config
    ): Promise<string> {
      const endMetric = metrics.startOperation('edit_file')
      try {
        const validPath = await validatePath(args.path, config)
    
        // Read the original content
        const content = await fs.readFile(validPath, 'utf-8')
        let modifiedContent = content
    
        // Track whether any edit was applied
        let appliedAnyEdit = false
    
        // Apply each edit
        for (const edit of args.edits) {
          const contentLines = modifiedContent.split('\n')
          let matchFound = false
    
          // Normalize line endings
          const normalizedOld = edit.oldText.replace(/\r\n/g, '\n')
          const normalizedNew = edit.newText.replace(/\r\n/g, '\n')
          const oldLines = normalizedOld.split('\n')
    
          // Validate edit
          if (oldLines.length === 0) {
            throw new InvalidArgumentsError('edit_file', 'Edit operation contains empty oldText')
          }
    
          // Find and replace the text
          for (let i = 0; i <= contentLines.length - oldLines.length; i++) {
            const potentialMatch = contentLines.slice(i, i + oldLines.length).join('\n')
            if (potentialMatch === normalizedOld) {
              // Preserve indentation
              const originalIndent = contentLines[i].match(/^\s*/)?.[0] || ''
              const newLines = normalizedNew.split('\n').map((line, j) => {
                if (j === 0) return originalIndent + line.trimStart()
                const oldIndent = oldLines[j]?.match(/^\s*/)?.[0] || ''
                const newIndent = line.match(/^\s*/)?.[0] || ''
                if (oldIndent && newIndent) {
                  const relativeIndent = newIndent.length - oldIndent.length
                  return originalIndent + ' '.repeat(Math.max(0, relativeIndent)) + line.trimStart()
                }
                return line
              })
    
              contentLines.splice(i, oldLines.length, ...newLines)
              modifiedContent = contentLines.join('\n')
              matchFound = true
              appliedAnyEdit = true
              break
            }
          }
    
          if (!matchFound) {
            throw new Error(`Could not find exact match for edit:\n${edit.oldText}`)
          }
        }
    
        // If no edits were applied, return early
        if (!appliedAnyEdit) {
          return 'No changes made - all edit patterns were empty or not found'
        }
    
        // Generate diff
        const diff = createUnifiedDiff(content, modifiedContent, validPath)
    
        // Write file if not a dry run
        if (!args.dryRun) {
          await fs.writeFile(validPath, modifiedContent, 'utf-8')
          await logger.debug(`Successfully edited file: ${validPath}`)
        }
    
        endMetric()
        return diff
      } catch (error) {
        metrics.recordError('edit_file')
        throw error
      }
    }
  • Zod schemas defining EditOperation (single replacement) and EditFileArgsSchema (full input: path, array of edits, dryRun flag).
    export const EditOperation = z.object({
      oldText: z.string().describe('Text to search for - must match exactly'),
      newText: z.string().describe('Text to replace with'),
    })
    
    /**
     * Schema for edit_file arguments
     */
    export const EditFileArgsSchema = z.object({
      path: z.string().describe('Path to the file to edit'),
      edits: z.array(EditOperation).describe('List of edit operations to perform'),
      dryRun: z.boolean().default(false).describe('Preview changes using git-style diff format'),
    })
  • src/index.ts:263-268 (registration)
    Tool registration in the list_tools handler: defines name 'edit_file', description, and converts EditFileArgsSchema to JSON schema for MCP protocol.
    name: 'edit_file',
    description:
      'Make line-based edits to a text file. Each edit replaces exact line sequences ' +
      'with new content. Returns a git-style diff showing the changes made. ' +
      'Only works within allowed directories.',
    inputSchema: zodToJsonSchema(EditFileArgsSchema) as ToolInput,
  • Dispatch handler case in main CallToolRequest handler: parses arguments with EditFileArgsSchema and invokes editFile function.
    case 'edit_file': {
      const parsed = EditFileArgsSchema.safeParse(a)
      if (!parsed.success) {
        throw new FileSystemError(`Invalid arguments for ${name}`, 'INVALID_ARGS', undefined, {
          errors: parsed.error.format(),
        })
      }
    
      const result = await editFile(parsed.data, config)
    
      endMetric()
      return {
        content: [{ type: 'text', text: result }],
      }
    }
  • createUnifiedDiff helper used by editFile to generate git-style unified diff wrapped in markdown code block.
    function createUnifiedDiff(
      originalContent: string,
      modifiedContent: string,
      filePath: string
    ): string {
      const diff = createTwoFilesPatch(
        filePath,
        filePath,
        originalContent,
        modifiedContent,
        'Original',
        'Modified'
      )
    
      // Find enough backticks to safely wrap the diff
      let numBackticks = 3
      while (diff.includes('`'.repeat(numBackticks))) {
        numBackticks++
      }
    
      return `${'`'.repeat(numBackticks)}diff\n${diff}${'`'.repeat(numBackticks)}\n\n`
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively communicates that this is a mutation tool ('Make line-based edits'), describes the return format ('Returns a git-style diff'), and adds important constraints ('Only works within allowed directories'). It doesn't mention error handling, permissions, or rate limits, but covers core behavioral aspects well.

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?

Three sentences with zero waste: first states the core purpose, second explains the editing method, third covers return value and constraint. Each sentence earns its place by providing essential information without redundancy. The structure is front-loaded with the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description does well by explaining what the tool does, how it works, what it returns, and important constraints. It could be more complete by mentioning error cases or the format of the git-style diff, but covers the essential context given the complexity.

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 already documents all three parameters thoroughly. The description adds some context by mentioning 'exact line sequences' which relates to the 'oldText' parameter, but doesn't provide additional semantic meaning beyond what's in the schema. This meets the baseline for high schema coverage.

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

Purpose5/5

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

The description clearly states the specific action ('Make line-based edits'), the resource ('to a text file'), and the method ('replaces exact line sequences with new content'). It distinguishes from siblings like 'write_file' by specifying line-based editing rather than overwriting entire files, and from 'read_file' by being a mutation operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about when to use this tool ('Only works within allowed directories'), which helps differentiate it from unrestricted file operations. However, it doesn't explicitly mention when NOT to use it or name specific alternatives among the sibling tools (e.g., 'write_file' for full file replacement).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.