What it does
chp-mcp sets spending controls on AI agents. It enforces budget caps and routes spending above defined human-in-the-loop (HITL) thresholds for approval. Each decision is recorded with a signed audit hash.
It suits teams whose AI agents can commit spend and who need explicit spending limits, a human checkpoint above a set amount, and a verifiable record of approvals.
The publisher's materials do not describe setup steps, supported clients or configuration details.
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
io.github.icohangar-ops/chp-mcp
Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
v0.1.2As shown on registry.modelcontextprotocol.io when we last read it