AI agents call working_context to retrieve information from THOUGHT without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without a description, classification confidence is reduced. The tool name 'working_context' most likely retrieves or queries the current working context from the persistent memory system, consistent with other Read-category tools on this server (query, recall, scan). However, the lack of documentation prevents ruling out that it could perform modifications.
From the tool's definition Tool name 'working_context' suggests retrieval of current context or state from the memory server. No description provided. Based on naming convention in sibling tools (browse_topic, list_topics, query, recall, scan), appears to be a read operation.
Attacks that exploit this kind of access
working_context. It is categorised as a Read tool in the THOUGHT MCP Server, which means it retrieves data without modifying state.
Register the THOUGHT MCP server in PolicyLayer and add a rule for working_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 THOUGHT. Nothing to install.
working_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 working_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 working_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.
working_context is provided by the THOUGHT MCP server (rnbbarrett/thought-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 →