Start a new context for a task. Reads <context-name>-context.yaml file from the assets directory. Combines prompts from all referenced files (personas, rules, mcps, actions) to provide context for AI development.
AI agents call start-context to retrieve information from Context Compose without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads a YAML configuration file and assembles/combines content from referenced files to provide context. It performs file reads with no described side effects, data modification, or execution of commands. The combination of prompts is a data-retrieval and aggregation operation.
From the tool's definition Reads <context-name>-context.yaml file from the assets directory. Combines prompts from all referenced files (personas, rules, mcps, actions) to provide context
Attacks that exploit this kind of access
Start a new context for a task. Reads <context-name>-context.yaml file from the assets directory. Combines prompts from all referenced files (personas, rules, mcps, actions) to provide context for AI development. It is categorised as a Read tool in the Context Compose MCP Server, which means it retrieves data without modifying state.
Register the Context Compose MCP server in PolicyLayer and add a rule for start-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 Context Compose. Nothing to install.
start-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 start-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 start-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.
start-context is provided by the Context Compose MCP server (lazylagom/context-compose-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 →