read_document
AI agents call read_document 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.
Despite empty description, the tool name and server functionality strongly suggest this retrieves document data from the Mnemosyne knowledge graph system. This is a Read operation (no side effects), but confidence is moderate due to missing description and medium severity due to potential access to sensitive knowledge graph contents depending on OAuth scoping and data sensitivity.
From the tool's definition Tool name 'read_document' combined with server context enabling 'query...knowledge graphs through SPARQL queries' and 'manage...graphs' indicates document retrieval.
Attacks that exploit this kind of access
read_document. 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 read_document: 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.
read_document 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 read_document 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 read_document. 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.
read_document 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 →