Skip to main content
Requires the Agents permission. Tools in this group are hidden from tools/list and refused on call when your plan does not grant it.

​
agent_duplicate

Write Copy an agent, optionally into a sub-account. Copies the configuration; the duplicate still needs agent_train before its knowledge works. Passing userId to place it in another user’s account is accepted only from an account owner. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.
​
string
Sub-account owner id. Omit to act on your own data.

​
agent_get

Read-only One agent’s full configuration: personality, intent, instructions, FAQs, follow-ups and booking action. Read this out to the user when they are choosing an existing agent. Configuration only: for what it actually said use agent_logs, for how it would answer a specific question agent_query, and for volumes agent_stats. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.

​
agent_list

Read-only AI agents configured for this account. CHAT agents reply to prospects in the inbox, CONTENT agents draft LinkedIn posts, and the rest are specialised assistants. Start here when the user asks about automated replies, and show them agent_get so they can judge the fit before anything is attached. An agent writes replies; a persona (persona_list) decides who qualifies; a knowledge base (kb_list) is the material an agent draws on. Attaching one to a campaign is campaign_update — and it answers real prospects by itself, so never attach one unasked. Requires the “Agents” permission on the plan.

​
Parameters

​
CHAT | VOICE | CONTENT | CAMPAIGN | REPORTING
Filter by type.
​
string
Free-text search.
​
boolean
default:"false"
Include conversation and booking counts.

​
agent_logs

Read-only What an agent was asked and what it answered — the trace to read when its replies look wrong. What it actually said in real conversations. To try a hypothetical instead, without sending anything, use agent_query; to read the prospect-facing thread use conversation_get. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.
​
integer (min 1)
default:"1"
1-indexed page number.

​
agent_query

Read-only Run a question through an agent against a real conversation, to see how it would answer. Returns the answer without sending anything — nothing reaches the prospect, which makes this the safe way to vet an agent before it goes active. For what it has already said use agent_logs. This is not a way to reply to anyone: sending an inbox message has no tool at all. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.
​
string
required
Context for the retrieval.
​
string
required
The question to put to the agent.

​
agent_stats

Read-only Conversations handled, replies sent and appointments booked, across all agents. Totals across every agent, not one — there is no per-agent breakdown here. To judge a single agent’s quality read agent_logs. Requires the “Agents” permission on the plan. No parameters.

​
agent_train

Write Rebuild the agent’s knowledge embeddings from its attached knowledge-base entries. Required after every kb_upsert or kb_attach, or the agent answers from stale material — this is the step most easily forgotten. It only re-indexes existing knowledge: it does not change the agent’s instructions (agent_upsert) and does not teach it anything not attached via kb_attach. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.

​
agent_upsert

Write Destructive
Marked destructive in the protocol — your MCP client asks for confirmation before running it.
Create an AI agent, or update one by passing agentId. A CHAT agent will reply to real prospects once it is active and attached to a campaign — set isActive: false while iterating on its instructions. The behaviour comes from personality (who it is), intent (what it is trying to achieve) and instructions (how it should write). This creates or edits the agent and nothing else. It does not attach it to a campaign (campaign_update), give it source material (kb_upsert then kb_attach), or build its embeddings (agent_train, which must run after any knowledge change). Test with agent_query before it touches a real conversation. There is no tool to delete an agent. Requires the “Agents” permission on the plan.

​
Parameters

​
string
Omit to create a new agent.
​
string
required
Internal name.
​
CHAT | VOICE | CONTENT | CAMPAIGN | REPORTING
CHAT for inbox replies, CONTENT for post drafting.
​
string
Company the agent represents; injected into its prompt.
​
OPENAI | ANTHROPIC | GEMINI | GROK | DEEPSEEK
Primary model provider. Must be connected.
​
OPENAI | ANTHROPIC | GEMINI | GROK | DEEPSEEK
Used when the primary provider errors.
​
string
Language code, e.g. “en”, “fr”, “de”, “it”, “pt”, “ja”.
​
string[]
Where the agent operates, e.g. [“linkedin”,“email”].
​
string
Who the agent is and how it carries itself.
​
string
The outcome it is steering the conversation toward.
​
string
Concrete writing rules: tone, length, what to avoid.
​
string
Raw system prompt override. Usually leave unset.
​
string[]
Subjects the agent is allowed to discuss.
​
object[]
Canned answers the agent should use verbatim.
​
array of object (free-form)
Follow-up messages sent when a lead goes quiet.
​
string[]
Words the agent must never use. Field name is spelled this way in the schema.
​
integer (min 0)
Minutes to wait before replying, so it reads as human.
​
integer (min 1)
Cap on agent messages per conversation.
​
boolean
Stand down as soon as a human replies in the thread.
​
object
Situations in which the agent should stand down.
​
"APPOINTMENT"
Enable calendar booking.
​
object
Configuration for the agent’s booking action.
​
string[]
Share this agent with these sub-accounts.
​
boolean
Notify you when the agent replies.
​
boolean
Whether the agent runs. Keep false while drafting.

​
kb_attach

Write Include or exclude a knowledge entry for one agent. Run agent_train afterwards or the change has no effect on answers. Scoped to one agent: it neither creates the entry (kb_upsert) nor deletes it, and there is no tool to delete a knowledge entry. Requires the “Agents” permission on the plan.

​
Parameters

​
string
required
AI agent id, from agent_list.
​
string
required
Knowledge-base entry id, from kb_list.
​
boolean
default:"true"
true attaches, false detaches.

​
kb_list

Read-only Source material agents can draw on: crawled URLs, uploaded files and pasted text. Account-wide. Which agent may use which entry is set per agent by kb_attach, so an entry listed here is not necessarily in use. Requires the “Agents” permission on the plan. No parameters.

​
kb_upsert

Write Destructive
Marked destructive in the protocol — your MCP client asks for confirmation before running it.
Add source material for agents. Type URL crawls a page, TEXT stores pasted content. Three steps, and skipping either of the last two leaves the agent unchanged: add it here, attach it with kb_attach, then rebuild with agent_train. Storing material does not change how the agent writes — that is agent_upsert instructions. Requires the “Agents” permission on the plan.

​
Parameters

​
string
Omit to create a new entry.
​
URL | FILE | TEXT
required
Filter by type.
​
string
Short label.
​
string
Required when type is URL.
​
string
Required when type is TEXT.