Searches for a regular expression pattern within the content of files in a specified directory (or current working directory). Can filter files by a glob pattern. Returns the lines containing matches, along with their file paths and line numbers. Args: pattern: The regular expression (regex) patt...
AI agents call search_text to retrieve information from Claude Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from the codebase without any side effects. It matches the Read category pattern of search/query operations that do not modify state. The severity is low because misuse would only expose code content an agent should already have access to, with no ability to modify, execute, or delete data.
From the tool's definition The tool 'searches for a regular expression pattern within the content of files' and 'Returns the lines containing matches, along with their file paths and line numbers.' It performs read-only operations with no modification, creation, deletion, or execution…
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access search_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Context, and nothing reaches the server without passing your rules. This is the rule we recommend for search_text:
{
"version": "1",
"default": "deny",
"tools": {
"search_text": {}
}
}search_text is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Searches for a regular expression pattern within the content of files in a specified directory (or current working directory). Can filter files by a glob pattern. Returns the lines containing matches, along with their file paths and line numbers. Args: pattern: The regular expression (regex) pattern to search for within file contents (e.g., 'function\\s+myFunction', 'import\\s+\\{.*\\}\\s+from\\s+.*'). path: Optional: The absolute path to the directory to search within. If omitted, searches the current working directory. include: Optional: A glob pattern to filter which files are searched (e.g., '*.js', '*.{ts,tsx}', 'src/'). If omitted, searches all files (respecting potential global ignores). Returns: A dictionary containing search results with file paths, line numbers, and matching lines. It is categorised as a Read tool in the Claude Context MCP Server, which means it retrieves data without modifying state.
Register the Claude Context MCP server in PolicyLayer and add a rule for search_text: 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 Claude Context. Nothing to install.
search_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_text 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.
Set action: deny in the PolicyLayer policy for search_text. 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.
search_text is provided by the Claude Context MCP server (zilliztech/claude-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Claude Context tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Claude Context tools catalogued and risk-classified — across an index of 42,500+ MCP servers.