Decapsulate a shared secret using a KEM secret key
AI agents call pqc_decapsulate to retrieve information from Post-Quantum Cryptography MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Decapsulation is a read-only cryptographic operation that retrieves existing data (the shared secret) from an encapsulated form. It does not create, modify, delete, execute code, or initiate external operations. The operation is deterministic and reversible in nature, and its output depends only on the input ciphertext and the decapsulation key.
From the tool's definition The tool 'pqc_decapsulate' performs decapsulation of a shared secret using a KEM (Key Encapsulation Mechanism) secret key.
Attacks that exploit this kind of access
Decapsulate a shared secret using a KEM secret key. It is categorised as a Read tool in the Post-Quantum Cryptography MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Post-Quantum Cryptography MCP Server MCP server in PolicyLayer and add a rule for pqc_decapsulate: 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 Post-Quantum Cryptography MCP Server. Nothing to install.
pqc_decapsulate 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 pqc_decapsulate 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 pqc_decapsulate. 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.
pqc_decapsulate is provided by the Post-Quantum Cryptography MCP Server MCP server (scottdhughes/post-quantum-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 →