load_session_context
AI agents call load_session_context to retrieve information from Paper Distill MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to load or retrieve session state/context rather than create, modify, delete, or execute operations. Even though the description is empty, the name and context of a paper search and curation server suggest this is a query/retrieval operation. No evidence of side effects, execution, destructive actions, or financial impact. Low severity because reading session context poses minimal risk in itself.
From the tool's definition Tool name 'load_session_context' and sibling tools like 'init_session', 'ingest_research_context' indicate session and context retrieval without mutation.
Attacks that exploit this kind of access
load_session_context. It is categorised as a Read tool in the Paper Distill MCP MCP Server, which means it retrieves data without modifying state.
Register the Paper Distill MCP server in PolicyLayer and add a rule for load_session_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 Paper Distill MCP. Nothing to install.
load_session_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_session_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_session_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_session_context is provided by the Paper Distill MCP server (pypi:paper-distill-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 →