AI agents use MatchReplace to create or update resources in Fledgling — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fledgling environment.
An AI agent can call MatchReplace faster than any human can review — one bad instruction and it creates or modifies resources in Fledgling by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
MatchReplace. It is categorised as a Write tool in the Fledgling MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fledgling MCP server in PolicyLayer and add a rule for MatchReplace: 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 Fledgling. Nothing to install.
MatchReplace 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 MatchReplace 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 MatchReplace. 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.
MatchReplace is provided by the Fledgling MCP server (teaguesterling/fledgling). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.