--- canonical_url: "https://docs.composio.dev/toolkits/fuseai_mcp" markdown_url: "https://docs.composio.dev/toolkits/fuseai_mcp.md" product: "platform" version: null last_updated: null --- # FuseAI MCP FuseAI MCP lets authorized agents search prospects, manage lists and campaigns, work with email and LinkedIn inboxes, monitor signals, inspect analytics and website intent, manage integrations and settings, and run external or deep research. - **Category:** model context protocol - **Auth:** DCR_OAUTH - **Composio-managed OAuth available?** No - **Tools:** 16 - **Triggers:** 0 - **Slug:** `FUSEAI_MCP` - **Version:** 00000000_00 ## Tools ### Agents **Slug:** `FUSEAI_MCP_AGENTS` The Agents / Signals feature: create, list, activate, and pause signal monitors — recurring lead/intent watchers (e.g. companies hiring SDRs, funding announcements, people engaging with a LinkedIn post, job postings). Hand off the user's full request here for anything about signal monitors or 'agents'. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | The user's full request about signal-monitor agents — create / list / activate / pause a monitor — with every detail given (signal type, keywords, list/URLs, locations, industries, titles, etc.). | ### Analytics **Slug:** `FUSEAI_MCP_ANALYTICS` Read-only performance dashboards & metrics: campaign metrics and trends (email / LinkedIn / dialer, with up-or-down deltas), dialer call analytics, prospecting/enrichment volumes, and team performance. Use for 'how is X performing / trending / up or down' questions. NOT the raw call log (that is power_dialer), and NOT for building or editing campaigns (that is campaigns). #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | A read-only analytics / performance-metrics question — campaign metrics & trends, dialer analytics, prospecting volumes, or team performance. Examples: 'how are my emails trending this month', 'is my dialer connect rate up or down', 'team performance this quarter'. | ### Ask fuse brain **Slug:** `FUSEAI_MCP_ASK_FUSE_BRAIN` Ask the Fuse Brain — living relationship files for ENGAGED contacts/companies, built from the team's real emails, LinkedIn messages, calls and meetings. Best tool for questions about existing relationships: history, needs, objections, commitments, deal state ('what does Dana care about?', 'which contacts mentioned budget?', 'where did the Acme deal stall?', 'who is waiting on us?'). Answers cite the contacts/companies used. Not for cold prospects: no file exists until a contact engages. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `question` | string | Yes | The question about tracked contacts/companies, self-contained (the tool does not see the chat). General ('which contacts mentioned budget concerns?', 'who is closest to buying?') or specific ('what does Dana at Acme care about?', 'where did the Initech deal stall?'). | | `focusName` | string | No | The contact or company name/domain the question is about, when it targets someone specific. Omit for general questions. | ### Automations **Slug:** `FUSEAI_MCP_AUTOMATIONS` Create and manage AUTOMATIONS — scheduled or event-triggered multi-step rules (website/news monitors with Slack digests, follow-up drafts, auto-enrolment into campaigns, CRM saves, AI steps, and rules that listen to or act in the user's connected apps: Google Calendar, Google Sheets, Notion, Typeform, Zendesk, Airtable, Asana, Linear, ...). Route here for anything recurring — 'daily', 'every time', 'whenever', 'monitor' — or any if-this-then-that request ('automate X when Y', 'when a Typeform response arrives...', 'before each calendar meeting...'), for connecting an app an automation needs, for 'I connected , continue', and for inspecting, editing, pausing, resuming, deleting, or asking about the runs of an existing automation / rule. Pass the user's full request (verbatim) as `request`. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | The user's full automation request, verbatim plus every detail needed — e.g. 'monitor bbcnews.com daily for robotics articles and DM me a summary on Slack', 'every time someone replies to a campaign, add them to my Hot Leads list', 'whenever an ICP-matching company visits the website, find its decision makers and enrol them in my Q3 outbound campaign', 'when a new Typeform response arrives, save the person and DM me', 'an hour before each Google Calendar meeting, brief me on the attendees', 'pause my website-visitor automation', 'did my news automation run today?', or an edit of an existing automation (include its automationId). Include any confirmation the user gave ('yes, activate it'). When the user says they connected an app and wants to continue (the Connect card's Continue sends only a short 'I connected ' message), pass the ORIGINAL automation request from this conversation again in full, together with the note that the app is now connected and anything the user added. | ### Campaigns **Slug:** `FUSEAI_MCP_CAMPAIGNS` Outreach campaigns and their email/LinkedIn/dialer SEQUENCES, end to end: list/create/update/duplicate/delete campaigns; build, generate, edit, reorder, test and preview sequence steps; ATTACH LISTS to a campaign (this is how you set up reaching a list of people, including system lists like All Website Visitors — attaching to an ALREADY-ACTIVE campaign enrolls its contacts in the background, while a draft campaign enrolls at launch); manage leads (pause/resume, activity); templates; and per-campaign performance metrics + trends. NEW campaigns built here stay DRAFTS until the user asks to launch; an existing active campaign keeps running. (For cross-feature dashboards — dialer/prospecting/team analytics — use analytics instead.) #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | What to do in Campaigns, in natural language. Include any list/campaign names or ids you already know. E.g. 'create a campaign named Spring Outreach, attach list , generate the sequence and leave it as a draft', 'add the All Website Visitors list to my Q2 campaign', 'show the leads in campaign X who replied', or 'list my campaigns'. Only include an instruction to activate/launch when the USER asked to launch in their own words — building a campaign or attaching a list ends in a draft, and a conditional like 'activate if valid' is never appropriate. | ### Deep research start **Slug:** `FUSEAI_MCP_DEEP_RESEARCH_START` Starts an asynchronous Fuse Deep Research run: over several minutes it researches the request across the web in the background and produces a markdown report, plus — when the request is to find people or companies — a new Fuse prospect list. Runs bill credits. ONLY call this when the user EXPLICITLY asks for "deep research", or confirms they want Deep Research after you offered it. For a general research/find-X request that does not say deep, do NOT call this — use the quick `research` tool, or ask the user whether they want quick research (immediate answer) or Deep Research (background, 5-20 minutes, report + prospect list) and wait for their choice. Returns immediately with a runId; it can NEVER wait for or preview results in the same call. After starting, call deep_research_status with the runId to check progress (suggest the user checks back in a few minutes). Pass the user's full request as `query`, an optional short `listName` when a list is expected, and `effort` if specified. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `query` | string | Yes | The full deep-research request in the user's own words — the topic to research across the web. | | `effort` | string | No | | | `listName` | string | No | | | `idempotencyKey` | string | No | Optional retry-safety key: calls with the same key return the SAME run instead of starting (and billing) a second one. Omit to always start a fresh run. | ### Deep research status **Slug:** `FUSEAI_MCP_DEEP_RESEARCH_STATUS` Checks a Fuse Deep Research run started with deep_research_start. Returns the run status (queued/planning/running/generating_csv/uploading/completed/failed/cancelled) and, once completed, the full markdown research report plus the id of any produced prospect list. Use it whenever the user asks whether their research is done or wants the results. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `runId` | string | Yes | The runId returned by deep_research_start. | ### Inbox **Slug:** `FUSEAI_MCP_INBOX` Use for anything in the user's inbox / messaging: reading, sending, flagging (read/archive/spam/delete), and tagging emails; AI-drafting email or LinkedIn replies; approving/declining/skipping pending auto-replies; and LinkedIn messaging (chats, messages, connections, invitations). Pass a clear, self-contained natural-language request. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | What to do in the inbox/messaging: read/send/flag/tag emails, AI-draft replies, approve/decline/skip auto-replies, or read/send LinkedIn messages, invitations, and connections. | ### Integrations **Slug:** `FUSEAI_MCP_INTEGRATIONS` CRM & integrations: connection status, CRM Fields/sync settings, owner mapping, pulling/pushing contacts & companies to the connected CRM (HubSpot/Salesforce/Zoho/Pipedrive/Attio), custom contact properties, and Slack notifications. Pass the full task as `request`. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | An integrations task: CRM connection status, CRM field/sync settings, owner mapping, pulling/pushing data to the CRM, custom contact properties, or Slack settings. | ### Power dialer **Slug:** `FUSEAI_MCP_POWER_DIALER` Power Dialer — call history (READ-ONLY). Use for questions about the user's recent calls / call history. Cannot place or manage live calls. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | A question about the user's power-dialer call history. | ### Prospect lists **Slug:** `FUSEAI_MCP_PROSPECT_LISTS` Manage the user's prospect lists: list lists (including the system/auto lists — All Website Visitors, All Saved Contacts, All Leads, All Enriched Contacts), view/search a list's rows, create/append/clean lists, smart columns, and resolve a list's real id. This is where you FIND the listId of a cohort (e.g. the people who visited the website) so a campaign can target it. NOT for finding brand-new prospects on the internet or the prospect database (that is prospect_search). #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | A natural-language instruction for managing prospect lists — e.g. 'list my lists', 'find the All Website Visitors list and give me its id', 'show what's in the SDR list', or 'create a list named Spring Prospects'. | ### Prospect search **Slug:** `FUSEAI_MCP_PROSPECT_SEARCH` Find people and companies, generate prospect/company search filters from a natural-language description, enrich contacts, and save prospects to lists. Use for anything in the Prospect Search area. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | What prospects or companies to find, the search filters to generate from a description, who to enrich, or which prospects to save to a list. | ### Research **Slug:** `FUSEAI_MCP_RESEARCH` EXTERNAL / internet research and web tasks: search & scrape the web (Firecrawl), Google Maps & Google Jobs lookups, building a prospect list from the web (EXA websets), internal knowledge-hub semantic search, and FuseAI how-to / navigation help. NOT for searching FuseAI's own prospect database — that's prospect_search. Examples: 'find recent funding news about Acme Corp', 'build me a list of AI infra startups in SF from the internet'. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | What to research on the internet (companies, people, places, jobs, news), a list to build from the web, an internal knowledge-hub lookup, or a FuseAI how-to/navigation question. | ### Settings **Slug:** `FUSEAI_MCP_SETTINGS` Account & workspace settings: company profile (name/website), enrichment preferences, team members & invitations, Knowledge Hub profiles, writing styles, ICPs (Ideal Customer Profiles), campaign visibility, a thin lifecycle view of existing Rules Engine automations (list/pause/resume/delete only — it does NOT create or edit automations), Deep Research provider keys (BYOK), and MANAGING the connected sending accounts — email accounts (settings/sharing/disconnect/SMTP connect/warmup start-pause), LinkedIn accounts, dialer phone numbers, and purchased sending domains & mailboxes. Also the door for API keys and billing/subscription questions (it can READ the current credit balance; everything else billing it explains is app-only). NOT for CRM connection/sync/owner-mapping. Pass the full settings task as `request`. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | An account/workspace settings task — e.g. 'update my company website to acme.io', 'invite jo@x.com as an admin', 'create an ICP for mid-market fintech', 'pause my website-visitor rule', 'disconnect john@acme.com', 'pause warmup for my Gmail account', 'save my Apollo API key', 'set my default knowledge hub profile'. | ### Smart actions **Slug:** `FUSEAI_MCP_SMART_ACTIONS` The Smart Actions feed — the home list of suggested next actions per contact, aggregated from website visits, signal-monitor matches, campaign replies, and ICP matches. Use it to answer 'what should I do next', to act on website-visitor or signal items one contact at a time (inspect -> enrich -> send), and to triage/execute the feed. Examples: 'what should I do next?', 'send the top suggested action', 'work through my website-visitor actions'. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | What to do with the Smart Actions feed — e.g. 'list my pending actions' or 'execute the top suggested action'. Self-contained; the sub-agent does not see the chat. | ### Website intent **Slug:** `FUSEAI_MCP_WEBSITE_INTENT` Use for Website Intent READ-ONLY reports + tracking config: who (companies/people/industries) is visiting the website, visitor analytics/trends, and the tracking setup (allowed domains, tag script, de-anonymization credits). NOT for acting on visitors — to turn website visitors into a list, reach them, or add them to a campaign, use prospect_lists (the 'All Website Visitors' list) + campaigns. Examples: 'which companies visited my site this month?', 'show my visitor trend', 'is my tracking tag live on acme.io?'. #### Input Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `request` | string | Yes | A website-intent question: a visitor report (companies/people/industries), visitor analytics/trends, or tracking config (domains, tag script, credits). To ACT on visitors (list/reach/campaign), that's prospect_lists + campaigns, not here. |