Skip to content

MCP Server

The MCP (Model Context Protocol) server is what makes scryer a two-way tool. You edit the visual diagram, and AI agents read and modify the same model programmatically.

The scryer-mcp binary ships bundled with the desktop app. When configured, your AI agent spawns it as a subprocess and communicates over stdio.

Everything the agent does through MCP shows up on your canvas in real-time. Add a node through the API? It appears in the editor. Move things around in the editor? The agent sees the updated positions on its next read.

ToolWhat it does
list_modelsList all saved models
get_modelFull model — all nodes, edges, flows, groups, source map
get_nodeScoped read of one node + its descendants + internal/external edges
get_rulesC4 modeling rules and workflow guidance
get_changesDiff since the agent last read the model
get_structureAnnotated project directory tree — manifests, infra configs, env templates
ToolWhat it does
set_modelCreate or replace a full model
set_nodeSet a node’s full subtree (children, edges)
add_nodesAdd new nodes
update_nodesUpdate existing node properties
delete_nodesRemove nodes (cascading to children)
add_edgesAdd new edges
update_edgesUpdate edge properties
delete_edgesRemove edges
set_flowsDefine behavioral flows with steps and branches
delete_flowRemove a flow
update_source_mapLink nodes/flows to source files
set_groupsOrganize nodes into groups
validate_modelCheck the model against C4 rules
ToolWhat it does
get_taskGet the next piece of implementation work — dependency-ordered, with inherited contracts

Agents don’t always need the full model. The MCP server provides three levels of detail:

  • get_model — everything. Use once at the start of a session to understand the full picture.
  • get_node — a focused subtree. Use when working on one container or component. Returns the target node, its descendants, internal edges, and external edges with context.
  • get_changes — just the diff. After the initial read, use this to see what changed since the last read. Efficient for keeping track of user edits.

When an agent models your architecture through MCP, it follows a level-by-level approach:

  1. System level first — persons, systems, external systems, and system-level edges
  2. Container level — all containers inside a system, plus container-level edges
  3. Component level — only when asked for deeper detail

Each level is validated for edge completeness. The agent builds top-down and fixes any warnings before going deeper.