search_and_replace

THE RISK

Medium Risk

Why search_and_replace needs a policy

This tool modifies file contents by replacing matched patterns with new text, which is a reversible write operation. The dry-run mode confirms it can also perform actual writes. High severity because it can modify code across many files in a codebase. It doesn't inherently delete/destroy data (replacements can be undone), so Write is the most appropriate category rather than Destructive.

From the tool's definition 'Search for patterns and replace them with new text (supports dry-run mode)'

Documented attack patterns abuse exactly the kind of access search_and_replace gives an agent:

POLICY

How to control search_and_replace

PolicyLayer is an MCP gateway — it sits between your AI agents and CodeSeeker-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_and_replace:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_and_replace": {
      "limits": [
        {
          "counter": "search_and_replace_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

search_and_replace stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register CodeSeeker-MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More CodeSeeker-MCP tools

Execute interactive_search Launch interactive TUI search mode (note: this starts an interactive session) Write code_refactor Refactor code structures like function names, class names, etc. Write bulk_replace Perform multiple search and replace operations in a single command Read basic_search Perform a basic text search using ugrep with optional filters and formatting Read boolean_search Perform Google-like Boolean search with AND, OR, NOT operators Read check_ugrep_installation Check if ugrep is installed and get installation instructions Read code_structure_search Search for specific code structures like functions, classes and methods Read fuzzy_search Perform fuzzy search that finds approximate matches allowing character errors

All 12 CodeSeeker-MCP tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about search_and_replace

What does the search_and_replace tool do? +

Search for patterns and replace them with new text (supports dry-run mode). It is categorised as a Write tool in the CodeSeeker-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on search_and_replace? +

Register the CodeSeeker- MCP server in PolicyLayer and add a rule for search_and_replace: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CodeSeeker-MCP. Nothing to install.

What risk level is search_and_replace? +

search_and_replace is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit search_and_replace? +

Yes. Add a rate_limit block to the search_and_replace rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block search_and_replace completely? +

Set action: deny in the PolicyLayer policy for search_and_replace. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides search_and_replace? +

search_and_replace is provided by the CodeSeeker- MCP server (mixelpixx/codeseeker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every CodeSeeker-MCP tool call.

Start from CodeSeeker-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →