Install an MCP server to your Kilo configuration. Adds the server entry to kilo.jsonc so it
AI agents use mcpmarket_install to create or update resources in Mcp Mcpmarket — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Mcpmarket environment.
This tool modifies the Kilo configuration file (kilo.jsonc) by adding new MCP server entries. It is a Write operation as it creates/modifies configuration data. The severity is high because installing arbitrary MCP servers could introduce malicious servers into the agent's trusted configuration, expanding the attack surface significantly.
From the tool's definition 'Install an MCP server to your Kilo configuration. Adds the server entry to kilo.jsonc'
Attacks that exploit this kind of access
Install an MCP server to your Kilo configuration. Adds the server entry to kilo.jsonc so it. It is categorised as a Write tool in the Mcp Mcpmarket MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Mcpmarket MCP server in PolicyLayer and add a rule for mcpmarket_install: 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 Mcpmarket. Nothing to install.
mcpmarket_install 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 mcpmarket_install 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 mcpmarket_install. 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.
mcpmarket_install is provided by the Mcp Mcpmarket MCP server (xzeroone/mcp-mcpmarket). 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 →