AI agents call fetch_content to retrieve information from ContextCore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The ContextCore server is explicitly a local-first indexing and search system. The 'fetch_content' tool, combined with context from sibling retrieval tools (get_file_content, get_codebase_context) and the server's stated purpose of retrieving 'relevant chunks for AI tools', indicates this is a Read operation—it queries and retrieves indexed content without side effects.
From the tool's definition Tool named 'fetch_content' with empty description. Based on sibling tools like 'get_file_content', 'get_codebase_context', and 'list_files', this server is designed for content retrieval and indexing.
Documented attack patterns abuse exactly the kind of access fetch_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ContextCore, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_content:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_content": {}
}
}fetch_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
fetch_content. It is categorised as a Read tool in the ContextCore MCP Server, which means it retrieves data without modifying state.
Register the ContextCore MCP server in PolicyLayer and add a rule for fetch_content: 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 ContextCore. Nothing to install.
fetch_content 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 fetch_content 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 fetch_content. 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.
fetch_content is provided by the ContextCore MCP server (lucifer-ux/contextcore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ContextCore, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 ContextCore tools catalogued and risk-classified — across an index of 43,000+ MCP servers.