Apply sed pattern to multiple files matching a glob pattern
AI agents use sed_multifile to create or update resources in MCP SmallEdit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP SmallEdit environment.
sed_multifile modifies file contents using pattern replacement, which is a Write operation (reversible data modification). Severity is medium because: (1) it affects multiple files via glob matching, increasing blast radius, (2) modifications are reversible (can be undone via restore_backup sibling tool), (3) no deletion or financial impact.
From the tool's definition Tool applies sed pattern modifications to multiple files - sed is a stream editor that modifies file contents. Description states 'Apply sed pattern to multiple files matching a glob pattern', indicating reversible modifications across multiple targets.
Attacks that exploit this kind of access
Apply sed pattern to multiple files matching a glob pattern. It is categorised as a Write tool in the MCP SmallEdit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP SmallEdit MCP server in PolicyLayer and add a rule for sed_multifile: 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 MCP SmallEdit. Nothing to install.
sed_multifile is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the sed_multifile 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 sed_multifile. 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.
sed_multifile is provided by the MCP SmallEdit MCP server (mikeybeez/mcp-smalledit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →