rivomiDocs

Tool reference

All thirty rivomi MCP tools grouped by job, with the scope each needs, whether it spends credits, and its REST twin.

Use this page to choose a tool. Before calling it, read its live schema from MCP tools/list; the schema is authoritative for arguments, defaults and limits. Each tool's description also says what it does not do and names the tool that does.

$ marks the four tools that spend credits. Scope is the minimum the credential needs; see API keys and OAuth.

Choose the tool

NeedUse
Know the balance, senders and whether sending is allowedrivomi_get_workspace. Call it first.
Answer "how are we doing"rivomi_get_dashboard
Find peoplerivomi_search_prospects, then rivomi_get_prospect
Build an agentrivomi_create_agent → rivomi_update_agent_sequence → rivomi_set_agent_state
See who is waiting for approvalrivomi_list_agent_queue
Approve or reject themrivomi_review_queue
Pull a LinkedIn post's commentersrivomi_import_prospects with estimate_only: true first
Enrich, score and draft a listrivomi_process_list
Follow a long jobrivomi_get_run
Find threads needing an answerrivomi_list_conversations with needs_reply: true
Answer onerivomi_get_conversation, then rivomi_reply

Workspace

ToolScopeWhat it doesREST
rivomi_get_workspacereadPlan, credits left, spend block, senders and their headroom today, sending consentGET /v1/workspace
rivomi_get_dashboardreadThe funnel over 7d, 30d, 3m or month: found, qualified, invited, messaged, replied, spend, best sourcesGET /v1/dashboard

Agents

ToolScopeWhat it doesREST
rivomi_list_agentsreadEvery agent with state, totals and list_idGET /v1/agents
rivomi_get_agentreadOne agent in full: targeting, sequence, signals, sources, stats, recent runsGET /v1/agents/{id}
rivomi_list_agent_queuereadawaiting_review (drafted, nothing sent) and enrollments (mid-sequence)GET /v1/agents/{id}/queue
rivomi_create_agentwriteA draft agent from a name, one source and optional targeting. Finds nobody until launched.POST /v1/agents
rivomi_update_agent_targetingwriteWho the agent looks for. Each array sent replaces the whole array.PATCH /v1/agents/{id}/targeting
rivomi_update_agent_sequencewriteReplace the steps, goal, tone, review mode, daily capPATCH /v1/agents/{id}/sequence
rivomi_set_agent_statewritelive (launches and runs now, spends) or paused (holds everything)POST /v1/agents/{id}/state
rivomi_run_agent_now $writeRun a live agent's sources now instead of on the six-hourly schedulePOST /v1/agents/{id}/run
rivomi_review_queuesendApprove (queues real outreach) or reject (counter-example) waiting peoplePOST /v1/agents/{id}/queue/review

Prospects

ToolScopeWhat it doesREST
rivomi_search_prospectsreadFilter by text, score band, signal, list, fit label, sequence stage, replied, dateGET /v1/prospects
rivomi_get_prospectreadOne person: signals with what they wrote, score and reason, lists, drafts, sequences, messagesGET /v1/prospects/{id}
rivomi_update_prospectwriteSet fit (good, not, none) and notes. not also suppresses them.PATCH /v1/prospects/{id}
rivomi_research_prospect $writeAn AI research brief against what the workspace sells; replaces any earlier briefPOST /v1/prospects/{id}/research

Lists and imports

ToolScopeWhat it doesREST
rivomi_list_listsreadEvery list with member count and owning agentGET /v1/lists
rivomi_get_listreadOne list's pipeline breakdown and approved-but-unqueued countGET /v1/lists/{id}
rivomi_create_listwriteAn empty list. Its context sentence is read by the scorer and the drafter.POST /v1/lists
rivomi_update_list_memberswriteAdd and remove people. Membership only: nothing is queued or cancelled.POST /v1/lists/{id}/members
rivomi_process_list $writeRun enrich, score, draft over a list. Sends nothing.POST /v1/lists/{id}/process
rivomi_import_prospects $writePull a LinkedIn post's commenters (default) or likers into a list. estimate_only is free and needs only read.POST /v1/imports

Runs

ToolScopeWhat it doesREST
rivomi_list_runsreadLong jobs, newest first, by kind, status, agent, dateGET /v1/runs
rivomi_get_runreadOne run: finished, what it found, errors, itemised costGET /v1/runs/{id}
rivomi_abort_runwriteStop the rest of a run. Spent stays spent; found stays found.POST /v1/runs/{id}/abort

Outreach

ToolScopeWhat it doesREST
rivomi_list_enrollmentsreadEveryone in a sequence, their state and next step dueGET /v1/enrollments
rivomi_enroll_prospectssendQueue named people or a whole list. Anyone without an approved draft is skipped.POST /v1/enrollments
rivomi_set_enrollment_statesendpaused, active, or stopped (irreversible, withdraws a pending invitation)POST /v1/enrollments/{id}/state

Inbox

ToolScopeWhat it doesREST
rivomi_list_conversationsreadThreads newest first. needs_reply returns unanswered replies plus accepted-but-never-messaged people.GET /v1/inbox
rivomi_get_conversationreadThe invitation note, then every message in orderGET /v1/inbox/{id}
rivomi_replysendSend a LinkedIn message now. No draft step, no undo, no merge fields.POST /v1/inbox/{id}/reply

REST only

Two reads exist only on REST, where there is no tool budget: GET /v1/templates (saved outbound copy) and GET /v1/senders (the long form of get_workspace.senders).

Call conventions

  • Reads take response_format: markdown (default, compact) or json (exact). Writes answer in JSON.
  • Lists return { total, count, offset, has_more, next_offset, items }. limit defaults to 25, caps at 200.
  • Long jobs return a run_id immediately. Poll rivomi_get_run until finished is true; runs usually take minutes.
  • Results over 25,000 characters are cut and say so. Narrow the filter rather than paging everything.

On this page