Skip to main content
The server registers around twenty tools across read, write, and execute scopes. Every tool ships with a structured description (WHAT it does / WHEN to use / WHAT to call NEXT) so the model gets useful guidance without you spelling each call out.

Discovery

The first thing a new chat does is load the pleyor-workflows skill from pleyor://skills/workflows. The skill teaches the patterns; the tools execute them.
ToolScopeUse it when
searchagents:readFind an agent, app, model, node, asset, or run by name fragment.
who_am_inoneConfirm which org the connector is bound to.
suggest_modelagents:readPick a model variant for a kind (image_generation, etc.) + use_case.
get_effective_portsagents:readResolve the actual port list for a node type given its config (some nodes have dynamic-arity ports).
get_run_inputs_schemaagents:readDiscover what inputs an agent expects before trigger_run.
estimate_run_costagents:readPreview credit cost before kicking off a run.

Building & editing graphs

ToolScopeUse it when
view_agentagents:readShow an agent’s current graph. Returns structured nodes/edges AND renders the canvas inline.
create_agentagents:writeBuild a new agent from a GraphSpec. Auto-layouts, validates, saves.
replace_graphagents:writeReplace an existing agent’s graph with a new GraphSpec. The only mutation tool — no add_node / update_node; design the whole graph and replace.
validate_graphagents:readValidate a spec before saving. Returns typed errors with next_action hints.
update_agentagents:writeUpdate agent metadata (name, description, etc.).
clone_agentagents:writeDuplicate an existing agent.
delete_agentagents:writeSoft-delete an agent.
restore_versionagents:writeRoll back to a saved version.

Running & monitoring

ToolScopeUse it when
trigger_runruns:executeRun an agent with optional inputs. Returns the new run_id.
trigger_appapps:executeRun a published app with the values its input schema expects.
wait_for_runruns:readBlock until a run reaches completed / failed / cancelled / paused. Pass timeout_ms up to 110000 to bound the wait. Almost always preferable to polling pleyor://runs/{id}.
cancel_runruns:executeCancel an in-progress run.
list_runsruns:readList recent runs, filtered by agent_id / status.

Publishing & sharing

ToolScopeUse it when
publish_appapps:executeTurn an agent into a public app with a defined inputSchema.
share_agent / unshare_agentagents:writeGenerate or revoke a read-only share link.
submit_reviewapps:executeSubmit an app for review (when reviews are enabled).
upload_assetassets:writeUpload an image / video / audio / file as a Pleyor asset that downstream nodes can reference.

Workflow skill

The server’s top-level instructions field directs new agents to read pleyor://skills/workflows — a markdown playbook covering:
  • The mental model (agents, nodes, ports, runs, apps, versions, assets)
  • 6 canonical workflow patterns (text→image, image→video, brand-aware multimodal, branching, fan-out, human-in-the-loop)
  • Build / edit / run / reuse / wait / iterate playbooks
  • An error-recovery playbook keyed on the typed error.code returned from failed tools
  • Cost-aware patterns and anti-patterns
It’s served directly off the MCP server (not an external HTTPS URL) so it can’t drift across deploys and stays consistent with the server version you’re talking to.

See also

Resources

The pleyor:// reads your assistant should make before designing.

Errors

The error codes, what they mean, and how to recover.