What it does
DCL Trust Oracle is an MCP server that audits the outputs of AI and LLM agents. Its publisher describes it as covering policy evaluation, a tamper-evident chain and AI safety. It is listed in the security category.
The publisher's description points to use cases where agent outputs must be checked against a policy and where the audit results need to be kept in a tamper-evident form.
According to the publisher's description, access is paid through the x402 protocol in USDC on the Base network.
Limitations and requirements
Payment is made through the x402 protocol in USDC on the Base network, as stated in the publisher's description.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
v2.3.1As shown on registry.modelcontextprotocol.io when we last read it