Executors for the MCP tools. All real work (running clj-kondo, Malli validation, project reflection, AI calls, scaffolding + the verify loop) lives here; the core stays a pure catalog. Each executor takes (args deps) and returns result data; throwing is fine — the dispatch maps it to an isError result.
Tier 0 (BOU-100): read/analyze. Tier 1 (BOU-101): generate — scaffold/write to disk (reversible via git) then run the closed verify loop (boundary.mcp.shell.verify).
Executors for the MCP tools. All real work (running clj-kondo, Malli validation, project reflection, AI calls, scaffolding + the verify loop) lives here; the core stays a pure catalog. Each executor takes (args deps) and returns result data; throwing is fine — the dispatch maps it to an isError result. Tier 0 (BOU-100): read/analyze. Tier 1 (BOU-101): generate — scaffold/write to disk (reversible via git) then run the closed verify loop (boundary.mcp.shell.verify).
(run deps name args)Execute tool name with args (a map) and deps ({:system-source
:ai-provider :scaffolder :test-runner :audit :evaluator :migrator
:db-query}). Returns result data, or nil if name is not a known tool.
Execute tool `name` with `args` (a map) and `deps` ({:system-source
:ai-provider :scaffolder :test-runner :audit :evaluator :migrator
:db-query}). Returns result data, or nil if `name` is not a known tool.cljdoc builds & hosts documentation for Clojure/Script libraries
| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |