Load relevant context for a project. Use personality_mode to shape retrieval: historian (default, newest-first with causality), prophet (ranked by prediction score), archaeologist (most-dormant first), minimalist (raw summaries only).
AI agents call load_context to retrieve information from Semantic Context MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval operation with no side effects. It queries stored context data and returns results ranked by different criteria (recency, prediction score, dormancy, or raw format), but does not create, modify, delete, or execute any external operations. The personality_mode parameter only affects how results are ranked and presented, not what data is altered or what external actions are triggered.
From the tool's definition Tool description states it 'Load[s] relevant context for a project' with configurable retrieval modes (historian, prophet, archaeologist, minimalist). No modification, deletion, or execution of external operations is indicated.
Attacks that exploit this kind of access
Load relevant context for a project. Use personality_mode to shape retrieval: historian (default, newest-first with causality), prophet (ranked by prediction score), archaeologist (most-dormant first), minimalist (raw summaries only). It is categorised as a Read tool in the Semantic Context MCP MCP Server, which means it retrieves data without modifying state.
Register the Semantic Context MCP server in PolicyLayer and add a rule for load_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 Semantic Context MCP. Nothing to install.
load_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 load_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 load_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.
load_context is provided by the Semantic Context MCP server (semanticintent/semantic-wake-intelligence-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 →