Low Risk

workspace_grep

Search for a regex pattern across files in your workspace using ripgrep. Returns structured results grouped by file with line numbers and context. Supports glob filtering, case sensitivity control, and context lines. Much faster than running grep via workspace_exec.

Risk signalsAccepts file system path (path)

Part of the ArcAgent MCP server.

workspace_grep is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE ARCAGENT MCP →

Free to start. No card required.

AI agents call workspace_grep to retrieve information from ArcAgent MCP 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 workspace_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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "workspace_grep": {}
  }
}

See the full ArcAgent MCP policy for all 45 tools.

Get this rule live on your own ArcAgent MCP server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY ARCAGENT MCP →

View all 45 tools →

These attack patterns abuse exactly the kind of access workspace_grep gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so workspace_grep only ever does what you allow.

SECURE ARCAGENT MCP →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the workspace_grep tool do? +

Search for a regex pattern across files in your workspace using ripgrep. Returns structured results grouped by file with line numbers and context. Supports glob filtering, case sensitivity control, and context lines. Much faster than running grep via workspace_exec.. It is categorised as a Read tool in the ArcAgent MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on workspace_grep? +

Register the ArcAgent MCP server in PolicyLayer and add a rule for workspace_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 ArcAgent MCP. Nothing to install.

What risk level is workspace_grep? +

workspace_grep is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit workspace_grep? +

Yes. Add a rate_limit block to the workspace_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.

How do I block workspace_grep completely? +

Set action: deny in the PolicyLayer policy for workspace_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.

What MCP server provides workspace_grep? +

workspace_grep is provided by the ArcAgent MCP server (araujota/arcagent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ArcAgent MCP tool call.

Deterministic rules across all 45 ArcAgent MCP 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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.