Funkel AI

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Run LinkedIn and email outreach: find leads, manage campaigns, and reply to prospects.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Funkel AI": {
      "url": "https://api.funkel.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (51)

• list_apps read-only

  List the products/apps owned by the request scope's user. Returns a summary (count, brief one-liner, and a list of {id, name, description, url}) with no timestamps or internal flags. Use this for product inventory or explicit product-switch/disambiguation questions. A normal product-scoped request already carries an app_id in Scope; do not call this just to discover which product to use for product-aware actions.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_product_context read-only

  Read the selected product's name, site, description, ICP summary, language, Product Brain availability, and dashboard link. No provider credentials or raw unbounded configuration are returned.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_lists read-only

  List unarchived lead lists in the selected product. Returns exact total and bounded pages. A list's cached lead count is not used for the total.

  Parameters:

  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_list read-only

  Read one unarchived list in the selected product and its exact member count. Does not return contacts; use list_list_contacts.

  Parameters:

  • list_id (required) — string — List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_list_contacts read-only

  List contacts in one unarchived list in the selected product. Returns exact total and bounded pages. Does not expose email or provider identifiers.

  Parameters:

  • list_id (required) — string — List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_schedule read-only

  List pending, approved, or failed scheduled actions in the selected product, optionally for one campaign. Returns one bounded page and its exact total. Completed actions are not included.

  Parameters:

  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)
  • campaign_id — string — Optional campaign id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_scheduled_action read-only

  Read one action in the selected product: campaign, lead, type, state, scheduled and executed timestamps. Does not return provider metadata or a message body.

  Parameters:

  • action_id (required) — string — Scheduled action id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_reminders read-only

  List open or done lead reminders in the selected product with exact total and bounded pages. Default is open. This read does not complete a reminder.

  Parameters:

  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)
  • status — string — Reminder state

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_insights read-only

  List account-scoped and selected-product-scoped open insights. Each item labels its actual scope; account insights are not product-only. Exact total and bounded pages.

  Parameters:

  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_insight read-only

  Read one insight and its evidence for the selected product, or an explicitly account-scoped insight. Read-only; proposed changes never run here.

  Parameters:

  • insight_id (required) — string — Insight id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_operator_tasks read-only

  List durable Operator tasks in the selected product. Returns bounded pages, exact total, task status, version, and links. Read-only.

  Parameters:

  • limit — integer — Page size (default 20; max 50)
  • offset — integer — Page offset (default 0)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_operator_task read-only

  Read one durable Operator task in the selected product with its step states, action states, safe summaries, version, and progress. Does not return executable arguments or raw provider errors.

  Parameters:

  • task_id (required) — string — Task id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_access read-only

  Read current account access for Operator and campaign actions in the selected product. Operator requires active paid or lifetime entitlement; campaign actions also accept active beta. Feature flags are account-wide. This snapshot is not an action authorization or credit quote.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• create_note destructive

  Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date. One request_key can be applied only once; a changed intent with the same key fails. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • lead_id (required) — string — Lead id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • request_key (required) — string — Stable unique request identity (8-128 chars)
  • body (required) — string — Note or reminder text (max 5000 chars)
  • reminder_at — string — Optional RFC3339 reminder due date
  • reminder_body — string — Required when reminder_at is set
  • confirmation_token — string — One-use approval token; omit on first call

  Hints: read-only no · destructive yes · idempotent no · open-world no

• create_reminder destructive

  Create a scoped note or reminder after an explicit confirmation of the exact lead, body, and due date. One request_key can be applied only once; a changed intent with the same key fails. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • lead_id (required) — string — Lead id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • request_key (required) — string — Stable unique request identity (8-128 chars)
  • body (required) — string — Note or reminder text (max 5000 chars)
  • reminder_at (required) — string — Required RFC3339 reminder due date
  • confirmation_token — string — One-use approval token; omit on first call

  Hints: read-only no · destructive yes · idempotent no · open-world no

• save_preference destructive

  Save one selected-product Operator preference after explicit approval. The value is bounded JSON data, not a system instruction. Existing keys update. No provider credentials or tokens are accepted. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • key (required) — string — Preference key (1-100 chars; no secret names)
  • value (required) — string — JSON value (max 600 bytes)
  • reason — string — Why this preference should be saved
  • confirmation_token — string — Approval token; omit on first call

  Hints: read-only no · destructive yes · idempotent no · open-world no

• rename_list destructive

  Rename one unarchived list in the selected product after explicit approval. Supply its current name to reject stale changes; include the full new description. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • list_id (required) — string — List id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • expected_name (required) — string — Current list name
  • name (required) — string — New name (1-100 chars)
  • description (required) — string — New full description
  • confirmation_token — string — Approval token; omit on first call

  Hints: read-only no · destructive yes · idempotent no · open-world no

• control_operator_task destructive

  Pause, resume, cancel, or retry a durable Operator task after exact approval. Supply its current version. Retry also requires one failed idempotent local-read step; completed effects cannot replay. A pause may not stop an already executing provider call. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • task_id (required) — string — Task id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • operation (required) — string — Task transition
  • expected_version (required) — integer — Current task version
  • step_id — string — Required failed step id for retry (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token — string — One-use approval token; omit on first call

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• list_agents read-only

  List the specialist agents in the product/app the request is scoped to. Returns a summary (count, brief one-liner, and a list of {id, name, status, type, role, one-line icp_summary}). Internal agent types are mapped to product-facing roles such as lead_finder. Full ICP filters / config are collapsed to a one-liner — call get_agent (later) to load full detail. Use this to ground questions like 'how many specialist agents do I have?' or 'which Lead Finder agents are active?'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_agent_sources read-only

  Read X and Hacker News listening settings for one owned agent, including sources not configured yet. Use list_agents to identify the agent. If configured is false, use configure_agent_source to propose exact searches and enable listening after approval. If configured is true and searches exist, use set_agent_source_listening to toggle without changing searches. A draft or paused agent does not collect until activated. LinkedIn signal groups are separate.

  Parameters:

  • agent_id (required) — string — Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • app_id — string — Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• set_agent_source_listening destructive

  Pause or resume only an existing X or Hacker News source on an agent. First read get_agent_sources. If configured is false or searches are empty, use configure_agent_source instead. The first call shows exact approval; a second user-approved call commits. Saved searches, budgets, LinkedIn resolution and other sources stay unchanged. A draft or paused agent does not collect until activated. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • agent_id (required) — string — Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • source (required) — string — One source
  • enabled (required) — boolean
  • app_id — string — Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token — string — One-use approval token, omit before approval
  • expected_updated_at — string — Version from get_agent_sources; optional on first call

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• configure_agent_source destructive

  Configure X or Hacker News searches for one owned agent and set source listening. First call get_agent_sources. If no source exists, propose 1-10 precise searches from the user's request and saved ICP; do not invent a broad search without showing it. If a source exists, show its current searches and only replace them when the user asks to change them. This tool previews the exact searches, enabled state, and LinkedIn resolution choice, then requires explicit approval. It does not activate a draft or paused agent. For an already configured source whose searches need no change, use set_agent_source_listening instead. X needs a connected X account for collection. Hacker News uses its public search provider. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • agent_id (required) — string — Owned agent ID (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • source (required) — string — Source to configure
  • queries (required) — array — Exact search phrases to save, 1-10
  • enabled (required) — boolean — Whether source listening should be enabled after approval
  • app_id — string — Product ID; required for MCP accounts with multiple products (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token — string — One-use approval token; omit before approval
  • expected_updated_at — string — Version from get_agent_sources; optional on first call
  • auto_resolve_linkedin — boolean — Hacker News only; automatically resolve high-confidence leads through LinkedIn, which may use credits

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• list_campaigns read-only

  List the campaigns in the app the request is scoped to (excludes archived). Returns a summary (count, brief one-liner, and a list of {id, name, status, agent_id, list_id}). Settings JSON is intentionally omitted; call get_campaign for current workflow, sender, and action detail. Status values: 'draft', 'active', 'paused'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_campaign read-only

  Read one campaign in the selected product. Returns updated_at for exact approved settings changes, plus workflow, sender assignments, schedule, review mode, observed action state, and readiness blockers. Empty templates are not claimed as generated messages. No sending or activation occurs.

  Parameters:

  • campaign_id (required) — string — Campaign id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• update_campaign_settings destructive

  Change a campaign's manual review, send window, or sender assignments in the selected product. Read get_campaign first and copy its updated_at as expected_updated_at. Omitted settings remain unchanged. Explicit null sender clears one platform. First call returns an exact approval preview; approved execution saves all changes atomically. It never activates, enrolls, or sends. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • campaign_id (required) — string — Owned campaign id from get_campaign (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • schedule — object — Full send window; all fields required when supplied
  • review_mode — boolean — Require manual review before outreach
  • confirmation_token — string — One-use approval token; omit on first call
  • account_assignments — object — Only supplied platforms change
  • expected_updated_at — string — Exact updated_at from get_campaign; may be omitted for a server-filled first preview

  Hints: read-only no · destructive yes · idempotent no · open-world no

• get_daily_priorities read-only

  Rank up to four live operational starting points with source IDs and links. Connected senders and insights count across the account; leads, actions, campaigns, and unread messages count within the selected product. Read only.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_sender_health read-only

  Show account-wide connected sender health and separate readiness for campaign assignments in the selected product. An account-wide connection does not prove a campaign has a usable sender.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_analytics read-only

  Return product- or campaign-scoped activity in a UTC lookback interval. Completed actions and invitations use executed_at; connections and recorded replies use lead event timestamps. These are separate event counts, not one conversion cohort. Default 7 days, max 90.

  Parameters:

  • scope — string — Aggregation level. Default 'app'.
  • days_back — integer — Lookback window in days (default 7)
  • campaign_id — string — Campaign id (required when scope='campaign') (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• find_leads read-only

  Search leads in the app the request is scoped to. Returns bounded named summaries and IDs, never full rows. Use get_lead to load full detail for a specific id. Default source is 'discovered' (agent-found, awaiting approval); pass source='approved' to search leads already in campaigns. Optional 'search' keyword runs an ILIKE across name/company/headline; optional 'status' narrows by lead status. If results are thin, surface the count and ASK the user before broadening the filters — do not silently relax constraints.

  Parameters:

  • limit (required) — integer — Max number of leads to return (1..50)
  • search — string — Optional keyword (matches name, company, or headline)
  • source — string — Lead source. Default 'discovered'.
  • status — string — Optional status filter (e.g. 'pending', 'approved', 'rejected')

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_lead read-only

  Return full detail for a single lead by id, INCLUDING the derived reply_state and opt_out flags. Always call this before drafting or sending a message — a lead whose reply_state is 'replied', 'rejected', or 'opted_out', or whose opt_out is true, must NEVER be drafted to or messaged. Use source='approved' for leads in active campaigns; default 'discovered' is for agent-found leads awaiting approval.

  Parameters:

  • lead_id (required) — string — Lead id (from a prior find_leads result) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • source — string — Lead source. Default 'discovered'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_conversation_context read-only

  Return bounded conversation context for one lead or conversation in the request scope: lead profile, product/campaign context, last real messages, recent notes, open reminders, and Reply Assistant follow-up suggestions. Use this before meeting prep, reply planning, or questions about what happened with a lead. Read-only; does not draft or send messages.

  Parameters:

  • limit — integer — Number of recent messages to return (default 12, max 20)
  • lead_id — string — Lead id from find_leads/get_lead or a follow-up result (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • conversation_id — string — Conversation id from inbox/follow-up context (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_inbox_queue read-only

  List reply-needed conversations or due follow-ups in the selected product. One predicate determines both the total and page. AI drafts are not counted as sent replies. Limit 50; use offset for later pages.

  Parameters:

  • mode (required) — string — Queue type
  • limit — integer — Maximum rows (default 20, max 50)
  • offset — integer — Pagination offset (default 0)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_operator_files read-only

  List up to 20 files uploaded to any of your Operator threads in the selected product. Returns file IDs and metadata only, never bytes or extracted text. A file can be used for a same-product LinkedIn reply, not another product or email reply.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• prepare_conversation_reply read-only

  Prepare one exact local inbound reply. Returns recipient, sender, channel, inbound revision, final signed body, and optional owned file identity. Never sends. Files are available only for supported connected LinkedIn conversations in the selected product.

  Parameters:

  • conversation_id (required) — string — Local conversation id (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • body (required) — string — Full proposed body. A configured booking link is tracked in the final preview
  • attachment_id — string — Optional file ID from list_operator_files. LinkedIn replies only (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• send_conversation_reply destructive

  Send one exact prepared reply to the latest inbound message after explicit human approval. Provide the complete prepare_conversation_reply result, its attachment_id when present, and a stable request_key. A timeout is uncertain and cannot be retried automatically. LinkedIn files are supported; email files are unavailable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • prepared (required) — object — Exact prepare_conversation_reply result; all fields required by server validation
  • request_key (required) — string — Stable unique request identity, 8-128 chars
  • attachment_id — string — Exact prepared file ID when present (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • confirmation_token — string — One-use approval token; omit on first call
  • reply_as_confirmed — boolean — Explicitly confirm using another rep's sender

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• get_reply_attempt read-only

  Read one reply attempt by its stable request_key in the selected product. Returns actual delivery evidence and next_action. Uncertain delivery requires manual provider review unless an exact outgoing provider message is confirmed. Never retries or sends.

  Parameters:

  • request_key (required) — string — Stable request identity from send_conversation_reply, 8-128 characters

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_preferences read-only

  List up to 20 saved Operator preferences for the user and product in the request scope. Values are bounded, labeled customer data, and never override user instructions or system rules. Returns key, value, and source only. No provider credentials or tokens are returned.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_external_leads

  Search LinkedIn for fresh people leads from the request user's connected account. Use this when the user describes leads to find by words, roles, companies, or market terms, rather than asking to search existing saved leads. Returns a server-owned session_id and up to 10 lead previews. To import the results, call import_search_leads_to_list with that session_id after the user asks to import all or selected leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • query (required) — string — Free-text people search, e.g. 'YC founders building AI devtools'
  • role — string — Optional job-title filter, e.g. 'Founder OR CEO'
  • limit — integer — Max results to return (1..10). Default 10.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• import_search_leads_to_list destructive

  Import lead rows from a prior search_external_leads session into a lead list. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms; second call with confirmation_token commits. provider_ids omitted means import every lead in the search session. Supply list_id for an existing list, or list_name to create a new list during the confirmed commit. After a committed result returns list_id, use that exact list_id when creating a campaign from the imported search leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • session_id (required) — string — Lead search session id returned by search_external_leads (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • list_id — string — Existing lead list id to import into (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • list_name — string — Name for a new list to create during the confirmed import when list_id is omitted
  • provider_ids — array — Optional selected provider ids from the search result. Omit to import all search results.
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world no

• create_campaign_draft destructive

  Create a draft campaign in the selected product. First show the exact campaign, agent, destination list, and any agent retargeting for approval. With agent_id and no list_id, use the agent's destination list; if absent, assign the product default list to both. An explicit different list retargets a draft agent only after approval. Never activate, discover, enroll, or send. If workflow_steps are omitted, create the standard 4-step flow. For custom steps ask about type, delay, message mode, template, and final step. In message_template use only {FirstName}, {LastName}, and {Company}. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • name (required) — string — Campaign name (1-100 chars)
  • list_id — string — Optional owned lead list id. With an agent, omitted means its destination list. Otherwise the product default list is used or created. (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_id — string — Optional agent id (from a prior list_agents) that supplies leads to this campaign (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • app_name — string — App name (used in the confirm preview)
  • workflow_steps — array — Optional custom workflow steps
  • cold_outreach_mode — string — Cold outreach mode (default 'invite')
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world no

• update_campaign_workflow destructive

  Update message content on existing steps in a draft or paused campaign. Prefer one-based message_order, which counts only message-bearing steps and automatically skips invite/follow steps: message_order 1, 2, 3 targets the first, second, and third messages even when raw workflow step 1 is an invite. step_order remains available only when an exact raw workflow order is already known. Provide exactly one selector plus the exact message_template for every item. In message_template use only {FirstName}, {LastName}, and {Company} personalization variables. This is a two-phase confirmed action: first call without confirmation_token returns a confirmation card; approved execution applies the exact stored workflow_messages through the campaign service. It never launches or sends. Always include campaign_name and app_name for a human-readable preview. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • campaign_id (required) — string — Campaign id from a prior list_campaigns result (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name (required) — string — Campaign name used in the confirmation preview
  • app_name (required) — string — App name used in the confirmation preview
  • workflow_messages (required) — array — Exact message content to persist; prefer message_order 1..N for ordinary campaign copy
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world no

• enable_campaign destructive

  Enable (resume) a paused or draft campaign. The campaign engine starts scheduling actions per the campaign's workflow. Two-phase: first call returns a confirmation token + preview; the user reviews and confirms; second call (with confirmation_token) commits. Activation pre-conditions (workflow steps, connected accounts) are validated by the underlying campaign service — the tool surfaces any failure as a structured error. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • campaign_id (required) — string — Campaign id (from a prior list_campaigns) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name (required) — string — Campaign name (used in the confirm preview)
  • app_name (required) — string — App name (used in the confirm preview)
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• draft_message

  Generate a personalised draft for one lead. Reads the lead's profile (industry, role, headline, optional reference hook) and returns a single message body. Does NOT send. After the user reviews and approves, call send_message to actually deliver. ALWAYS call get_lead first to inspect reply_state — refuse to draft for opted-out / replied / rejected leads. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • lead_id (required) — string — Lead id (from a prior find_leads / get_lead) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • tone — string — Voice register
  • reference — string — Optional specific hook (recent post, role transition, milestone) the user wants referenced

  Hints: read-only no · destructive no · idempotent no · open-world yes

• create_list

  Create a new lead list scoped to the request's app. Use this when the user wants to organise leads into a named bucket (e.g. 'Q4 Targets', 'Hot Founders'). The new list starts empty; populate it later via approve_leads with action='approve' and the new list_id, or by editing the list manually. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • name (required) — string — Display name for the list (1-100 chars)
  • description — string — Optional one-sentence description of what the list is for

  Hints: read-only no · destructive no · idempotent no · open-world no

• draft_icp_edit read-only

  Stage a proposed ICP edit for one agent. Returns a diff envelope (current vs proposed, fields_changed) so the user can review the change inline before applying it. Does NOT write — to actually apply the edit, call update_icp (confirm-tier) with the same agent_id and proposed fields. Use this when the user describes a change in plain language ('target Series A founders in EU' etc.); never call update_icp directly without first staging here so the user sees the before/after.

  Parameters:

  • agent_id (required) — string — Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • proposed_icp_filters — string — Optional structured filters JSON (job_titles, industries, regions, etc.)
  • proposed_icp_description — string — Free-text description of the new ICP

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• pause_campaign destructive

  Pause an active campaign. The campaign engine stops scheduling actions. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms or cancels; second call (with confirmation_token) commits the pause. Always include campaign_name + app_name so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • campaign_id (required) — string — Campaign id (from a prior list_campaigns) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name (required) — string — Campaign name (used in the confirm preview)
  • app_name (required) — string — App name (used in the confirm preview)
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• enable_agent destructive

  Enable (activate) a paused or draft agent so it begins discovering leads on its schedule. Two-phase: first call returns a confirmation token + preview; the user reviews and confirms; second call (with confirmation_token) commits. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • agent_id (required) — string — Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_name (required) — string — Agent name (used in the confirm preview)
  • app_name (required) — string — App name (used in the confirm preview)
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• pause_agent destructive

  Pause an active agent so it stops discovering new leads. The agent's existing leads remain in the list. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms or cancels; second call (with confirmation_token) commits the pause. Always include agent_name + app_name so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • agent_id (required) — string — Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_name (required) — string — Agent name (used in the confirm preview)
  • app_name (required) — string — App name (used in the confirm preview)
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• approve_leads destructive

  Approve or reject one or more discovered leads. Two-phase: first call returns a confirmation token + preview; the user reviews an inline card and confirms; second call (with confirmation_token) commits the status flip. action='approve' requires campaign_id (the campaign the leads will be associated with); action='reject' does not. The tool stamps each lead's status + reviewed_at + campaign_id; downstream campaign-engine pipelines ingest approved leads through their normal path. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • action (required) — string — Decision applied to every lead in lead_ids
  • lead_ids (required) — array — Discovered lead ids (from a prior find_leads result)
  • count — integer — Number of leads in the batch (used in the confirm preview; mirrors len(lead_ids))
  • campaign_id — string — Required for action=approve; omitted for action=reject (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • campaign_name — string — Campaign name (used in the confirm preview)
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world yes

• update_icp destructive

  Apply an ICP edit (description and/or filters JSON) to one agent. Two-phase: first call returns a confirmation token + preview; the user reviews the diff inline and confirms; second call (with confirmation_token) commits. ALWAYS call draft_icp_edit first so the user sees a before/after; never call update_icp directly without staging a diff. Pre-populate agent_name in the schema args so the preview is human-readable. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • agent_id (required) — string — Agent id (from a prior list_agents) (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000)
  • agent_name — string — Agent name (used in the confirm preview)
  • icp_filters — object — New structured filters object. Use company_sizes and exclude_service_providers. excluded_companies accepts exact employer names or LinkedIn company URLs. URLs become slug names and remain separately in competitor_urls. Ask the user to verify the employer name. Omit to leave unchanged.
  • icp_description — string — New free-text ICP description (omit to leave unchanged)
  • industry_inputs — array — Explicit raw industry intent from draft_icp_edit ready_to_execute_args. Omit for canonical-only edits. Nested old metadata cannot restore removed raw intent.
  • confirmation_token — string — Phase-2 token (omit on phase-1)

  Hints: read-only no · destructive yes · idempotent no · open-world no

• create_agent destructive

  Create a new draft agent under the request's scoped app. Two-phase: first call previews every setting; second call after user confirmation creates it. The agent's ICP starts from the app's saved ICP; icp_filters keys you supply override only those keys, every other saved field (job_titles, mandatory_keywords, excluded_companies, company_sizes, ...) is kept as-is. Do not restate the full ICP from memory for a vague request like "set it up" — omit icp_filters entirely to inherit the saved ICP untouched, and only pass the specific keys the user actually asked to change. To deliberately clear a list field, pass it as an empty array. excluded_companies stores exact current employer names. If supplied a LinkedIn company URL, Operator saves its slug name there and retains the URL separately for competitor signals; ask the user to verify the name in the approval. Supply signals only when the user selects exact agent discovery signals; each signal must include its supported platform, category, key, label, enabled state, and config. An explicit empty signals array creates no signals. Without signals, defaults seed from the merged ICP filters. A requested keyword such as product launch can be a keyword_tracking_product_launch signal with config.keyword='product launch'. Ask for missing signal details; never claim a requested setting was saved if this schema cannot represent it. Over MCP: call this tool once, without confirmation_token. It runs right away and returns the result.

  Parameters:

  • name (required) — string — Display name for the new agent (1-100 chars)
  • type — string — Agent type (default 'signal')
  • signals — array — Exact agent discovery signals. Omit to seed from ICP; use [] for none.
  • app_name — string — App name (used in the confirm preview)
  • icp_filters — object — Optional structured ICP filters. Use job_titles, industries, regions, company_sizes, excluded_keywords, and exclude_service_providers. excluded_companies accepts exact employer names or LinkedIn company URLs. URLs become slug names and remain separately in competitor_urls. Ask the user to verify the employer name. Do not use unsupported excluded_industries.
  • max_signals — integer — Cap on enabled signals (default 15)
  • icp_description — string — Free-text ICP description for the new agent
  • confirmation_token — string — Phase-2 token (omit on phase-1)
  • linkedin_account_ids — array — Local UUIDs of the workspace LinkedIn accounts selected for searches. Use [] for none.

  Hints: read-only no · destructive yes · idempotent no · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.