Server-side regex text search over indexed project source files. Free tier: requires file_path (single file). Premium tier (XMP4_PREMIUM_GREP_WALK=true): allows file_glob multi-file walk. Prefer xmp4_tests_for/xmp4_usages for SCIP symbols — grep is for text not indexed (comments, literals, config...
Risk signalsAccepts file system path (file_path)
Part of the xmp4 — Semantic code knowledge for your stack server.
Free to start. No card required.
AI agents call xmp4_grep to retrieve information from xmp4 — Semantic code knowledge for your stack without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though xmp4_grep only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"xmp4_grep": {}
}
}See the full xmp4 — Semantic code knowledge for your stack policy for all 16 tools.
These attack patterns abuse exactly the kind of access xmp4_grep gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Server-side regex text search over indexed project source files. Free tier: requires file_path (single file). Premium tier (XMP4_PREMIUM_GREP_WALK=true): allows file_glob multi-file walk. Prefer xmp4_tests_for/xmp4_usages for SCIP symbols — grep is for text not indexed (comments, literals, config keys).. It is categorised as a Read tool in the xmp4 — Semantic code knowledge for your stack MCP Server, which means it retrieves data without modifying state.
Register the xmp4 — Semantic code knowledge for your stack MCP server in PolicyLayer and add a rule for xmp4_grep: 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 xmp4 — Semantic code knowledge for your stack. Nothing to install.
xmp4_grep 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 xmp4_grep 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 xmp4_grep. 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.
xmp4_grep is provided by the xmp4 — Semantic code knowledge for your stack MCP server (https://mcp.example4.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 xmp4 — Semantic code knowledge for your stack tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.