Agents

Agent identities and their access.

7 tools — 3 read, 4 write.

Tool		What it does
create_agent	write	Create an agent persona you own.
disable_agent	write	Disable an agent you own.
get_agent_access_space_items	read	List the items in ONE of your spaces (or private / shared) with the role one of your agents holds on each — the expanded view of get_agent_access_spaces.
get_agent_access_spaces	read	Show one of your agents' access by space: your private space, items shared with you, General, and every named space you are in — each with its item count, your
issue_agent_token	write	Mint a nous_pat_ token for one of your agents.
list_agents	read	List the agents you own in this org, with shared-resource count, active token count, and last-active time.
revoke_agent_token	write	Revoke a token belonging to one of your agents.

Calling these

Over MCP, find one with search_tools, then run it with execute_tool. Over REST, POST /api/capabilities/<tool> with the arguments as the JSON body. Either way, fetch the input schema for the tool you're about to call rather than guessing — get_tool_schema over MCP, or GET /api/capabilities?name=<tool> over REST.

See How the API works for auth, errors and the shared envelope.