AI agents call transfer_agent_context to retrieve information from Kontexta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool copies/reads existing context files from a project directory. 'COPY' and 'from a project' indicate a read/transfer operation retrieving existing files. However, since it transfers these files (likely writing them somewhere else), it could be Write. The description emphasizes 'from a project' suggesting extraction. Given ambiguity, Write is possible but Read is the primary action described.
From the tool's definition COPY existing agent context files (CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, etc.) from a project
Attacks that exploit this kind of access
COPY existing agent context files (CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, etc.) from a project. It is categorised as a Read tool in the Kontexta MCP Server, which means it retrieves data without modifying state.
Register the Kontexta MCP server in PolicyLayer and add a rule for transfer_agent_context: 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 Kontexta. Nothing to install.
transfer_agent_context 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 transfer_agent_context 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 transfer_agent_context. 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.
transfer_agent_context is provided by the Kontexta MCP server (safiyu/kontexta). 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 →