> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fuseai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools & limits

> What each Fuse MCP tool does, how to phrase requests, and the rate limits that apply.

The MCP server doesn't mirror REST endpoints one-to-one. Instead it exposes **one tool per Fuse feature area**, and each tool is an agent: it takes a natural-language `request`, carries out the work inside that feature (often several operations), and answers in plain text.

That changes how you use it. Rather than orchestrating calls, describe the outcome you want and let the tool do the orchestration:

> "In prospect\_lists: find my list of website visitors from July and tell me how many rows it has."

Requests should be **self-contained** — each call stands alone, so include the relevant names, dates, or ids rather than referring to "the list from before". Your assistant generally does this for you, but it explains why very terse follow-ups sometimes make the tool ask for clarification.

## The tools

| Tool              | What it covers                                                                                                                                                                                   |
| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `prospect_search` | Find people and companies in Fuse's database, build search filters from a description, enrich contacts, and save results to lists.                                                               |
| `prospect_lists`  | Manage your lists: browse and search rows, create or append lists, clean them up, work with smart columns, and resolve a list's id (including system lists like *All Website Visitors*).         |
| `campaigns`       | Outreach campaigns end to end: create and edit campaigns and their email/LinkedIn/dialer sequence steps, attach lists, manage leads, templates, and per-campaign metrics.                        |
| `inbox`           | Read, send, and organize email; draft replies with AI; approve or decline pending auto-replies; LinkedIn chats, messages, connections, and invitations.                                          |
| `agents`          | Signal monitors ("agents"): recurring watchers for things like companies hiring, funding announcements, or LinkedIn post engagement — create, list, activate, pause.                             |
| `smart_actions`   | The Smart Actions feed of suggested next steps per contact — review it, and act on items one contact at a time.                                                                                  |
| `analytics`       | Read-only dashboards: campaign performance and trends, dialer analytics, prospecting volumes, team performance.                                                                                  |
| `website_intent`  | Read-only website visitor intelligence — which companies and people visited, trends, and your tracking configuration.                                                                            |
| `power_dialer`    | Read-only call history. It cannot place calls.                                                                                                                                                   |
| `research`        | External web research: search and scrape the web, Google Maps and Jobs lookups, build a list from the open web, and search your knowledge hubs.                                                  |
| `settings`        | Account and workspace settings: company profile, team, Knowledge Hub profiles, writing styles, ICPs, automation rules, and connected sending accounts (email, LinkedIn, phone numbers, domains). |
| `integrations`    | CRM and integrations: connection status, field mappings, pulling/pushing contacts and companies to HubSpot, Salesforce, Zoho, Pipedrive, or Attio, and Slack notifications.                      |

Tool boundaries follow the app's navigation. When a job spans areas — say, "campaign the companies that visited my site" — the assistant chains tools: `prospect_lists` to resolve the *All Website Visitors* list, then `campaigns` to attach it.

## Deep Research

Two additional tools run Fuse's Deep Research agent, which is asynchronous because a run takes minutes, not seconds:

* `deep_research_start` begins a run and returns a `runId` immediately.
* `deep_research_status` reports progress for a `runId` and returns the report when the run completes.

A typical run takes **5–20 minutes**; your assistant polls `deep_research_status` in the meantime. Any prospect list the run produces also appears in your lists in the Fuse app, and the report is available there too.

## Behavior and safety

* Every tool runs **with your permissions** — it sees and touches only what your Fuse user can.
* Campaigns created or edited over MCP **stay drafts** until you explicitly ask to launch them; an already-active campaign keeps running while you edit.
* `analytics`, `website_intent`, and `power_dialer` are read-only by design.
* Tool errors come back as short plain-text messages (for example, "The tool could not complete the request.") rather than internal error details.

## Rate limits

MCP usage is limited per user, independently of your [REST API rate limits](/concepts/rate-limits):

| Window     | Limit          |
| ---------- | -------------- |
| Per minute | 60 requests    |
| Per day    | 5,000 requests |

Beyond a limit the server returns `429` with the code `RATE_LIMIT_EXCEEDED`, and your assistant should back off and retry. One conversational ask usually costs a handful of requests (a tool call plus the protocol handshake), so the limits are generous for interactive use.