Reads contextcache.json and returns full project context with module instructions and caching.
AI agents call get_context_from_config to retrieve information from Mcp Context Cache without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and delivers cached project context data without creating, modifying, deleting, or executing operations. It is purely a Read operation. Severity is low because reading configuration files poses minimal risk even if misused by an agent — the operation cannot damage systems, move money, or cause irreversible changes.
From the tool's definition Tool performs 'Reads contextcache.json and returns full project context' — a data retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Reads contextcache.json and returns full project context with module instructions and caching. It is categorised as a Read tool in the Mcp Context Cache MCP Server, which means it retrieves data without modifying state.
Register the Mcp Context Cache MCP server in PolicyLayer and add a rule for get_context_from_config: 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 Context Cache. Nothing to install.
get_context_from_config 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_context_from_config 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_context_from_config. 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_context_from_config is provided by the Mcp Context Cache MCP server (jdug-jadodev/mcp-caching). 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 →