AI agents call loadcontext to retrieve information from Project MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server purpose indicate this retrieves project knowledge graph data. While the description is empty (reducing confidence slightly), the pattern of sibling tools (startsession, endsession for lifecycle; buildcontext for creation; deletecontext for removal) suggests loadcontext is a read operation. No evidence suggests data modification, deletion, or external execution.
From the tool's definition Tool name 'loadcontext' suggests retrieving or loading existing context data. Given the server manages project knowledge graphs and provides context-building tools (advancedcontext, buildcontext), loadcontext most likely retrieves stored context rather than…
Documented attack patterns abuse exactly the kind of access loadcontext gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Project MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for loadcontext:
{
"version": "1",
"default": "deny",
"tools": {
"loadcontext": {}
}
}loadcontext 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.
loadcontext. It is categorised as a Read tool in the Project MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Project MCP Server MCP server in PolicyLayer and add a rule for loadcontext: 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 Project MCP Server. Nothing to install.
loadcontext 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 loadcontext 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 loadcontext. 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.
loadcontext is provided by the Project MCP Server MCP server (tejpalvirk/project). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Project MCP Server, 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.
6 Project MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.