Topic

security

4 min read

Store the Upstream Token in the Gateway, Not in Your MCP Config

Pasting a production bearer token into ~/.cursor/mcp.json means every engineer's laptop holds a credential that can call your billing API directly. The gateway should inject it; the agent client should never see it.

Read article
4 min read

Expose Three Operations, Not the Whole OpenAPI Spec

When you convert an entire OpenAPI doc into MCP tools, the agent sees 87 endpoints including the one that deletes a tenant. Per-operation exposure is the blast-radius control you actually want.

Read article
4 min read

MCP Security in Practice: Prompt Injection, Least Privilege, and Audit Logs

MCP turns external content into actions: a tool description or API response is text the model reads and trusts, which makes indirect prompt injection a real attack path. Here is a practical threat model and the controls that actually work, from scoped tokens to human-in-the-loop and audit logs.

Read article
4 min read

MCP Authentication Explained: OAuth 2.1 for Remote MCP Servers

Local stdio MCP servers inherit your CLI credentials, so nobody notices auth until they host one. Remote MCP servers require OAuth 2.1 with PKCE, metadata discovery, and short-lived tokens. Here is the full flow and the mistakes that get servers rejected by clients.

Read article