Security · Model Context Protocol · samugit83/redamon

Wiring a new tool the AI agent can call (not the recon pipeline): the tool registry, the phase map, the hardcoded dispatch chokepoint, and the duplicated execution paths that make a tool work in…

samugit83/redamon

Adding an LLM provider to RedAmon: the credential boundary (keys must never reach scan containers), prefix-routed model ids, and the provider registry.

samugit83/redamon

Adding, removing or changing a tool on RedAmon's INBOUND MCP server, where external agents connect in with a personal access token.

samugit83/redamon

The Priority Board's three-layer score model (rules BASE, REVIEW by the built-in AI or an MCP agent, a person's DECISION) and who may write which layer.

samugit83/redamon

Changing or adding a project setting / default value in RedAmon.

samugit83/redamon