set_working_memory
AI agents use set_working_memory to create or update resources in Metis Public Health — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metis Public Health environment.
The tool modifies working memory, which is a form of data creation/modification (Write category). It is reversible (memory can be overwritten or cleared) and does not delete data irreversibly or execute arbitrary code.
From the tool's definition Tool name 'set_working_memory' indicates modification of in-memory state. Sibling tools like 'add_memory_entry', 'add_journal_entry', and 'add_glossary_term' all perform Write operations (create/modify data), suggesting this tool fits the same pattern.
Attacks that exploit this kind of access
set_working_memory. It is categorised as a Write tool in the Metis Public Health MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for set_working_memory: 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 Metis Public Health. Nothing to install.
set_working_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_working_memory 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 set_working_memory. 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.
set_working_memory is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →