MCP tools

Reference the repo, sandbox, automation, model, log, and agent-run tools exposed by the Mogplex MCP endpoint.

Mogplex exposes 19 user-scoped tools. The client loads their current JSON schemas through tools/list, validates arguments locally when supported, and sends each call to the same service layer used by the v1 API.

Discovery and sandboxes

ToolScopeWhat it does
mogplex_list_reposreadList accessible repos and the GitHub installation id used by automations.
mogplex_list_agentsreadList user-owned and preset agents available to Flow nodes.
mogplex_list_modelsreadList enabled model ids.
mogplex_list_sandboxesreadList active or recent sandboxes, optionally by repo or status.
mogplex_create_sandboxwriteCreate or reuse a repo and branch sandbox.
mogplex_get_sandbox_logsreadRead install logs, dev-server logs, errors, and lifecycle events.

mogplex_create_sandbox consumes the existing launch event stream and returns when the launch succeeds or fails. It does not create a separate status-polling loop.

Automations

ToolScopeWhat it does
mogplex_list_automationsreadReturn a bounded, cursor-paginated page of graph-free summaries.
mogplex_get_automationreadRead one automation with its complete draft and published graphs.
mogplex_create_automationwriteCreate a draft, optionally from a complete validated graph.
mogplex_update_automationwriteUpdate metadata or replace the complete validated draft graph.
mogplex_publish_automationwriteValidate, version, and activate the draft.
mogplex_set_automation_modelwriteSet or clear an agent node's model override.
mogplex_trigger_automationwriteRun an active published automation for an owned repo.
mogplex_list_automation_runsreadList recent executions and node or dispatch summaries.
mogplex_get_automation_run_logsreadRead node runs, dispatch events, AI calls, errors, usage, and review findings.

Automation listing defaults to 50 records and accepts a maximum limit of 100. Pass nextCursor from one response back as cursor. The list response omits graphs; call mogplex_get_automation only when you need the full draft or published graph.

Agent runs

ToolScopeWhat it does
mogplex_start_agent_runwriteStart a Codex or Claude Code run in a repo sandbox.
mogplex_get_runreadRead current run state and metadata.
mogplex_get_run_eventsreadRead append-only run events.
mogplex_cancel_runwriteRequest cancellation of an active run.

Response shape

Successful calls include readable text for conversational clients and structuredContent for clients that consume JSON directly. Tool errors return the MCP error envelope with a stable machine-readable code such as BAD_REQUEST, UNAUTHORIZED, FORBIDDEN, or NOT_FOUND.

Call tools/list for the authoritative current JSON schemas. The Mogplex MCP endpoint reference documents the transport envelope and direct JSON-RPC request shape.

Edit on GitHub

On this page