Claude TypeScript MCP Servers

84 tools. 50 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

50 can modify or destroy data
34 read-only
84 tools total

Community server · catalogue entry verified 11/06/2026

How to control Claude TypeScript MCP Servers ↓

What Claude TypeScript MCP Servers exposes to your agents

Read (34) Write / Execute (48) Destructive / Financial (2)
Critical Risk

The most dangerous Claude TypeScript MCP Servers tools

50 of Claude TypeScript MCP Servers's 84 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Claude TypeScript MCP Servers

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude TypeScript MCP Servers, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "append_file": {
    "limits": [
      {
        "counter": "append_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "brave_local_search": {
    "limits": [
      {
        "counter": "brave_local_search_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Claude TypeScript MCP Servers — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CLAUDE TYPESCRIPT MCP SERVERS →

Free to start. No card required.

All 84 Claude TypeScript MCP Servers tools

EXECUTE 29 tools
Execute puppeteer_clear_input Clear an input field Execute batch_operations Execute multiple file operations efficiently. Supports transactional mode (rollback on error) and parallel exe Execute puppeteer_emulate_device Emulate a specific device Execute puppeteer_evaluate Execute JavaScript in the browser console Execute puppeteer_evaluate_in_frame Execute JavaScript in a specific frame Execute puppeteer_navigate Navigate to a URL Execute puppeteer_wait_for_function Wait for a JavaScript function to return true Execute puppeteer_wait_for_navigation Wait for page navigation to complete Execute puppeteer_wait_for_selector Wait for an element to appear on the page Execute puppeteer_wait_for_timeout Wait for a specified amount of time Execute compress_files Compress files into an archive. Supports zip, tar, and tar.gz formats. Requires appropriate tools (zip/tar) to Execute puppeteer_go_back Navigate back in browser history Execute puppeteer_go_forward Navigate forward in browser history Execute puppeteer_hover Hover over an element on the page Execute puppeteer_pdf Generate PDF from the current page Execute puppeteer_reload Reload the current page Execute puppeteer_screenshot Take a screenshot of the current page or a specific element Execute puppeteer_search_across_frames Search for elements across all frames Execute merge_pull_request Merge a pull request Execute puppeteer_add_script_tag Add a script tag to the page Execute puppeteer_authenticate Set HTTP authentication credentials Execute puppeteer_click Click an element on the page Execute puppeteer_fill Fill out an input field Execute puppeteer_keyboard_press Press a specific key or key combination Execute puppeteer_keyboard_type Type text with fine-grained control over typing speed Execute puppeteer_select Select an option from a select element Execute puppeteer_set_viewport Set the viewport size of the page Execute puppeteer_switch_to_frame Switch context to a specific frame Execute puppeteer_switch_to_main_frame Switch context back to the main frame
WRITE 19 tools
Write append_file Append content to the end of a file. Creates the file if it doesn Write extract_archive Extract files from an archive. Supports zip, tar, and tar.gz formats. Creates destination directory if it does Write add_issue_comment Add a comment to an existing issue Write copy_file Copy a file to a new location. Fails if destination exists unless overwrite is true. Both paths must be within Write create_branch Create a new branch in a GitHub repository Write create_directory Create directory or ensure it exists. Creates nested directories. Succeeds silently if already exists. Only wo Write create_file Create a new file (alias for write_file). Creates or overwrites a file. Only works within allowed directories. Write create_issue Create a new issue in a GitHub repository Write create_or_update_file Create or update a single file in a GitHub repository Write create_pull_request Create a new pull request in a GitHub repository Write create_release Create a new release for a repository Write create_repository Create a new GitHub repository Write edit_file Make edits to text files. Supports text replacement, line-based operations (replace/insert/delete), and regex Write move_file Move or rename files and directories. Fails if destination exists. Both paths must be within allowed directori Write puppeteer_set_cookies Set cookies for the current page Write push_files Push multiple files to a GitHub repository in a single commit Write update_issue Update an existing issue in a GitHub repository Write update_release Update an existing release Write write_file Create or overwrite a file. Caution: overwrites without warning. Handles text encoding. Only works within allo
READ 34 tools
Read brave_local_search Search local businesses, services, and places. Returns real-time data including address, phone, ratings, hours Read brave_web_search Keyword-based web search returning a list of search results. Each result includes title, description, and URL. Read directory_tree Get recursive tree view as JSON. Each entry has name, type (file/directory), and children for directories. 2-s Read fetch Fetch content from a specific URL. Use when you have an exact URL and need its full content. Extracts text as Read get_file_contents Get the contents of a file or directory from a GitHub repository Read get_file_info Get file/directory metadata: size, creation time, modified time, permissions, type. Only works within allowed Read get_issue Get details of a specific issue in a GitHub repository Read get_latest_release Get the latest release for a repository Read get_pull_request Get details of a specific pull request Read get_release Get a specific release by ID Read list_allowed_directories List directories this server can access. Read list_directory List files and directories in a path. Distinguished with [FILE] and [DIR] prefixes. Only works within allowed Read list_issues List issues in a GitHub repository with filtering options Read list_pull_requests List and filter repository pull requests Read list_releases List releases for a repository Read puppeteer_get_content Get the full HTML content of the page Read puppeteer_get_cookies Get all cookies for the current page Read puppeteer_get_element_info Get detailed information about an element Read puppeteer_get_frames Get information about all frames on the page Read puppeteer_get_text Get the text content of an element Read puppeteer_get_title Get the page title Read puppeteer_get_url Get the current page URL Read read_file Read file contents with proper encoding. Supports partial reading by byte range or line range. Encoding option Read read_multiple_files Read multiple files simultaneously. More efficient than reading one by one. Returns each file Read search_code Search for code across GitHub repositories Read search_content Search for content within files. Supports plain text and regex search. Returns matching lines with file path a Read search_files Recursively search files matching a pattern. Case-insensitive, partial name matching. Returns full paths. Only Read search_issues Search for issues and pull requests across GitHub repositories Read search_repositories Search for GitHub repositories Read search_users Search for users on GitHub Read sonar_multi_search Performs multiple related searches simultaneously and returns combined results. Ideal for complex research que Read sonar_search sonar_search Read sonar_search_with_timeout Performs a natural language search with a strict timeout to ensure fast responses. IMPORTANT: Ask in natural Read watch_file Check for file changes since a specific time. Due to MCP constraints, this is a one-time check, not continuous

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Claude TypeScript MCP Servers

Can an AI agent delete data through the Claude TypeScript MCP Servers MCP server? +

Yes. The Claude TypeScript MCP Servers server exposes 2 destructive tools including delete_file, delete_release. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Claude TypeScript MCP Servers? +

The Claude TypeScript MCP Servers server has 19 write tools including append_file, extract_archive, add_issue_comment. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Claude TypeScript MCP Servers.

How many tools does the Claude TypeScript MCP Servers MCP server expose? +

84 tools across 4 categories: Destructive, Execute, Read, Write. 34 are read-only. 50 can modify, create, or delete data.

How do I enforce a policy on Claude TypeScript MCP Servers? +

Register the Claude TypeScript MCP Servers MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Claude TypeScript MCP Servers tool call.

Deterministic rules across all 84 Claude TypeScript MCP Servers tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

84 Claude TypeScript MCP Servers tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.