get_workspace
AI agents call get_workspace to retrieve information from Mnemosyne MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix is a standard naming convention for retrieval operations. Given the sibling tools include read operations (check_document, context_bundle, document_digest) and more severe operations (delete, create_graph), this tool most likely retrieves workspace metadata or configuration without modifying state. Classified as Read with medium-high confidence due to the empty description reducing full certainty.
From the tool's definition Tool name 'get_workspace' strongly suggests a retrieval operation that fetches workspace data. The description is empty, which limits certainty, but the naming pattern ('get_' prefix) and context within a knowledge management system indicates read-only…
Attacks that exploit this kind of access
get_workspace. It is categorised as a Read tool in the Mnemosyne MCP MCP Server, which means it retrieves data without modifying state.
Register the Mnemosyne MCP server in PolicyLayer and add a rule for get_workspace: 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 Mnemosyne MCP. Nothing to install.
get_workspace 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 get_workspace 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 get_workspace. 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.
get_workspace is provided by the Mnemosyne MCP server (sophia-labs/mnemosyne-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 →