Resolve a live code collision with a peer BEFORE you write (Layer C resolution handoff). Call this when the Stop hook
AI agents call get_resolution_context to retrieve information from Kawa Code MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to query or retrieve collision resolution context from a live code session without modifying data. The 'BEFORE you write' language and 'get_' prefix indicate it performs read-only retrieval of resolution context to inform subsequent decisions. No write, deletion, code execution, or financial operations are evident.
From the tool's definition Tool name contains 'get_' and description indicates it 'Resolve[s]' and involves checking/querying collision state 'BEFORE you write', suggesting it retrieves context rather than modifies state.
Attacks that exploit this kind of access
Resolve a live code collision with a peer BEFORE you write (Layer C resolution handoff). Call this when the Stop hook. It is categorised as a Read tool in the Kawa Code MCP MCP Server, which means it retrieves data without modifying state.
Register the Kawa Code MCP server in PolicyLayer and add a rule for get_resolution_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 Kawa Code MCP. Nothing to install.
get_resolution_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 get_resolution_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 get_resolution_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.
get_resolution_context is provided by the Kawa Code MCP server (kawacode-ai/kawa.mcp). 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 →