Nerve is your AI Chief of Staff. Connect your Gmail, Calendar, and Slack, and Nerve reads everything and tells you what actually matters today. It generates daily briefings, drafts actions for your review, preps you for meetings, and runs a team of AI agents that learn how you work. One person runs like a team of ten. Built by NerveLabs Inc.

Connect Gmail, Google Calendar, and Slack with one click each. Nerve scans your email, calendar, and messages overnight, then delivers a morning briefing with priorities, meeting prep, and draft actions. A team of specialized AI agents (Chief of Staff, Growth, Revenue, Product, and more) work in the background. Nothing sends without your approval.

Is my data safe with Nerve?

Nerve only reads email, calendar, and Slack data you explicitly connect. Authentication is via Clerk (SOC 2 Type II certified). Data is stored in Upstash Redis (SOC 2 + GDPR compliant). AI processing uses Anthropic Claude, which does not train on customer data. All data is user-scoped and namespace-isolated.

How much does Nerve cost?

Nerve offers four tiers. Lite is free and includes one briefing per day. Pro is $29/month. Operator is $79/month with founding-member pricing locked for early adopters and a 1:1 strategy session with the founder. For Teams is $49/seat/month (5-seat minimum) with agent-as-a-service pricing that absorbs token costs. Contact patrick@getnerve.ai for enterprise pricing.

Which tools does Nerve integrate with today?

Gmail and Google Calendar via Google Workspace OAuth. Microsoft 365 (Outlook, Calendar, Teams) via Microsoft OAuth. Slack via Slack OAuth. Salesforce and HubSpot for CRM read and write. Zapier SDK opens access to 9,000+ additional apps. Plus optional connectors for LinkedIn (Unipile) and Google Drive. Voice access via iOS Shortcuts (Hey Siri, tell Nerve). MCP keys let other AI tools (Claude, Cowork) read and write Nerve state.

Can I cancel anytime?

Yes. Cancel from your account page in one click. No contracts on Lite, Pro, or Operator. For Teams pilots run 90 days with month-to-month after that. Revoking OAuth on any connector instantly stops Nerve from reading that source.

← MCP guides

MCP guides · Setup

MCP is simpler than the docs make it look. Here's the 30-minute version.

Name: Nerve by NerveLabs Inc.
Author: NerveLabs Inc.

If you have an MCP host (Claude Desktop, Claude Code, Cowork, or Nerve) and one MCP server, you have a working agent. The hard part is choosing which server to install first.

Try Nerve free Read Nerve's developer docs

The problem

Why this matters

Most MCP intros open with the protocol spec, JSON-RPC, capability negotiation, and 14 lines of YAML configuration. By the time you finish reading, you have not actually installed anything and you have lost an hour.

The reality is much simpler. MCP is a way to give an LLM tools through a standard interface. There is a host (where the LLM runs), there are servers (where the tools live), and there is a config file that tells the host which servers to talk to. That's it.

This guide is the version that gets you from zero to a working agent before lunch: which host to use, which server to install first, how to handle auth without losing a day, and what to do once your hello-world works.

What you get

What MCP unlocks here

Pick a host that does most of the work

Claude Desktop is the lowest-friction starting point: a config file, a server name, a path. Claude Code is identical for developers. Cowork and Nerve run as hosted agents and accept your MCP server URL via web UI. Skip OpenAI for now if you are MCP-first.

Start with one server, not seven

Gmail OR Calendar OR Filesystem. Pick the one whose data is the bottleneck in your day. Get it working end-to-end before adding more. Tool noise is the silent killer of MCP setups.

Auth is the hard part, accept it

OAuth is where you'll spend most of the time. Read the server's README before installing. Stripe down to least privilege. Workspace admin policies will sometimes block scopes; ask your admin or use a personal account for the prototype.

Make the agent do a recurring outcome on day one

Once the server is wired, do not just chat. Ask the agent for an actual deliverable: 'tell me what's overdue,' 'find me 30 minutes with X,' 'summarize what changed in folder Y since Tuesday.' Recurring outcomes are the test of whether the install was worth it.

Setup

Three steps to a working agent

Choose your host

Claude Desktop for solo prototyping. Claude Code if you live in the terminal. Cowork or Nerve if you want a hosted agent that runs without your laptop being open. All four speak the same MCP. Hosts are interchangeable; servers are reusable.

Install one server, end-to-end

Clone the server repo. Read the README for environment variables. Get OAuth working (this is the long part). Add the server to your host's config. Restart the host. Verify the tools show up. Verify a real call works (read one email, list five calendar events, list directory contents).

Give the agent a job

Stop chatting. Start asking for outcomes. 'Every morning, list the threads I have not replied to.' 'Find time with three people this week.' 'Summarize the doc folder for last month.' When the recurring outcome works, you are done. Add servers from there.

Signal

What people doing this say

Followed an MCP intro for two hours and got nowhere. Followed this approach (one host, one server, one outcome) and had an agent doing real work in 25 minutes.
Solo founder, healthtech (paraphrased)

The 'install seven servers and figure it out' approach is how most MCP setups die. One-at-a-time is the move.
Engineer-turned-operator

MCP is the easiest hard thing in AI right now. The protocol is simple. The decision-making (which host, which server, which outcome) is where 95% of the time goes.
Patrick Hillstrom, Nerve

FAQ

Common questions

Do I need to be a developer to set this up?

For Claude Desktop with a single server, no, you can copy a JSON config and follow a README. For more complex setups (multiple servers, custom auth, self-hosted servers), some familiarity with environment variables and OAuth helps. Cowork and Nerve hide most of the plumbing behind a web UI.

What's the difference between an MCP host and an MCP server?

Host = the thing the LLM runs in (Claude Desktop, Claude Code, Cowork, Nerve). Server = the thing that exposes tools (Gmail server, Calendar server, your custom server). Hosts call servers over a standard protocol. One host can talk to many servers.

Are MCP servers safe to install?

Treat them like browser extensions. Prefer official servers from the data provider when they exist. Read community server source code. Scope auth tokens to minimum permissions. Audit logs if the server provides them.

Can I build my own MCP server?

Yes. The SDK is straightforward in TypeScript and Python. Most founders only need to build their own when the data is proprietary (an internal database, a custom tool). For Gmail, Calendar, GitHub, Linear, Notion, and major CRMs, the community already shipped one worth using.

How does Nerve fit in?

Nerve is an MCP host AND an MCP server. As host: our agents call out to your stack via MCP. As server: we expose nerve_pipeline, nerve_briefing, nerve_calendar, and 50+ other tools that any MCP host can call. Plug your Nerve key into Claude Desktop or Cowork and you have an agent team your hosted LLM can drive.

Stop reading MCP docs. Install one server and feel the unlock.

Start free, no credit card

More MCP guides