Skip to main content
Glama

search_files

Search within files using a regex pattern to identify matching lines, displaying file paths and line numbers.

Instructions

Search for a regex pattern inside files. Returns matching lines with file and line number.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
directoryYesDirectory to search in
patternYesRegex pattern to search for
file_globNoGlob to filter files (e.g. '*.ts')
ignore_caseNoCase-insensitive search
max_resultsNoMax results to return (default 100)
workspace_rootNoWorkspace root directory (optional)

Implementation Reference

  • The core searchInFiles function that recursively walks a directory, reads files, and matches lines against a regex pattern. Returns matching file, line number, and content.
    async function searchInFiles(
      dir: string,
      pattern: string,
      options: { glob?: string; ignoreCase?: boolean; maxResults?: number }
    ): Promise<Array<{ file: string; line: number; content: string }>> {
      const results: Array<{ file: string; line: number; content: string }> = [];
      const max = options.maxResults ?? 100;
      const regex = new RegExp(pattern, options.ignoreCase ? "i" : "");
    
      async function walk(current: string) {
        if (results.length >= max) return;
        let entries;
        try {
          entries = await readdir(current, { withFileTypes: true });
        } catch {
          return;
        }
        for (const entry of entries) {
          if (results.length >= max) return;
          if (entry.name.startsWith(".") || entry.name === "node_modules" || entry.name === "dist") continue;
          const full = join(current, entry.name);
          if (entry.isDirectory()) {
            await walk(full);
          } else if (entry.isFile()) {
            if (options.glob && !matchGlob(entry.name, options.glob)) continue;
            try {
              const content = await readFile(full, "utf-8");
              const lines = content.split("\n");
              lines.forEach((line, idx) => {
                if (results.length < max && regex.test(line)) {
                  results.push({ file: full, line: idx + 1, content: line.trim() });
                }
              });
            } catch {
              // skip binary files
            }
          }
        }
      }
    
      await walk(dir);
      return results;
    }
  • Input schema for the 'search_files' tool, defining parameters: directory, pattern, file_glob, ignore_case, max_results, and workspace_root.
    {
      name: "search_files",
      description: "Search for a regex pattern inside files. Returns matching lines with file and line number.",
      inputSchema: {
        type: "object",
        properties: {
          directory: { type: "string", description: "Directory to search in" },
          pattern: { type: "string", description: "Regex pattern to search for" },
          file_glob: { type: "string", description: "Glob to filter files (e.g. '*.ts')" },
          ignore_case: { type: "boolean", description: "Case-insensitive search" },
          max_results: { type: "number", description: "Max results to return (default 100)" },
          workspace_root: { type: "string", description: "Workspace root directory (optional)" },
        },
  • The tool handler case for 'search_files' that resolves the workspace path, calls searchInFiles(), and formats the results as text output.
    case "search_files": {
      const dir = resolveWorkspacePath(a.directory as string, a.workspace_root as string | undefined);
      const results = await searchInFiles(dir, a.pattern as string, {
        glob: a.file_glob as string | undefined,
        ignoreCase: (a.ignore_case as boolean | undefined) ?? false,
        maxResults: (a.max_results as number | undefined) ?? 100,
      });
      if (results.length === 0) {
        return { content: [{ type: "text", text: "No matches found." }] };
      }
      const text = results
        .map((r) => `${r.file}:${r.line}: ${r.content}`)
        .join("\n");
      return { content: [{ type: "text", text: text }] };
    }
  • Helper function resolveWorkspacePath used by the handler to resolve relative paths against a workspace root or current working directory.
    function resolveWorkspacePath(filePath: string, workspaceRoot?: string): string {
      if (filePath.startsWith("/") || /^[A-Za-z]:/.test(filePath)) return filePath;
      const base = workspaceRoot ?? process.cwd();
      return resolve(join(base, filePath));
    }
  • Helper function matchGlob used by searchInFiles to filter filenames against a glob pattern (e.g. '*.ts') by converting glob to regex.
    function matchGlob(name: string, pattern: string): boolean {
      const escaped = pattern.replace(/[.+^${}()|[\]\\]/g, "\\$&").replace(/\*/g, ".*").replace(/\?/g, ".");
      return new RegExp(`^${escaped}$`).test(name);
    }
Behavior3/5

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 accurately describes the read-only search behavior and return format, but omits details like recursive search, case sensitivity behavior (only covered by schema), or performance limits beyond max_results.

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?

Two sentences, no fluff. Every word is necessary and informative. Efficiently communicates core purpose and output.

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's complexity (regex, glob, case-insensitive, max_results) and no output schema, the description is partially complete. It covers the basic search behavior but lacks details on recursion, glob semantics, and error handling.

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 coverage is 100%, so the description adds minimal extra meaning. It confirms the regex nature and output format, but does not explain nuances like default values for max_results or workspace_root usage.

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 searches for regex patterns inside files and returns matching lines with file and line number, providing a specific verb+resource. However, it does not differentiate from the sibling 'find_files', which likely searches filenames, reducing clarity for an agent deciding between them.

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 'find_files' or other file tools. It does not mention context, prerequisites, or exclusions, leaving the agent to infer usage.

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/KloutDevs/vscode-mcp'

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