Reads are automatic
Every write requires confirmation. Nothing changes in your systems without approval.
Connectors
Your backend, your helpdesk, your data.
Capabilities map to your own endpoints. Your team picks them up in Peeve Hand-Offs, syncing into your helpdesk if you keep one. Nothing about Peeve is a separate silo.
Stripeconnected
Slackconnected
Zendeskconnected
Custom MCP serveravailable
Custom API connectoravailable
Does real backend work
Beyond answers: look things up and take action in your systems.
Peeve doesn't just answer from a help center. Connect your own tools two ways (your MCP server or any REST API), and mid-conversation it reads live data (an order, an invoice, an account status) and takes real actions for your customers. No SDK, no integration project: minutes, not weeks.
Custom API ConnectorScale and up
Turn your existing REST API into something the assistant can use, built automatically from your API docs.
How it connects
01Paste your API docs URL.
02Peeve reads the docs and builds the connector: base URL, auth, every endpoint, each marked read or write.
03Add your API credentials (encrypted, per workspace).
04The assistant can now use your API in conversations.
At runtime. Read endpoints are called live to answer with current data. Write endpoints (a refund, a record update) always run through a confirmation step and a workspace allow-list.
Custom MCP ServerGrowth and up
Already run an MCP server? Peeve plugs straight into it. Your internal tools become things the assistant can do for customers.
How it connects
01Paste your MCP server URL (and an access token if it needs one).
02Peeve does a live handshake and discovers the tools your server exposes.
03You choose which of those tools the assistant is allowed to use.
At runtime. When the page alone can't answer, the assistant calls your MCP tools to fetch data or perform an action. Anything that changes state runs through the same confirm guardrail.
You pick what's enabled
Turn individual tools and endpoints on or off; the auto-built API connector is fully reviewable.
Credentials stay yours
Encrypted at rest per workspace and never shown again. The model never sees a token.
ConnectorPlan
Custom MCP ServerGrowth and up
Custom API ConnectorScale and up
The connector catalog
Every tool Peeve works with.
Connectors are available on Growth and above. A one-time import from another tool is included on every plan.
Outbound
Peeve acts on a system you run: deliver a hand-off, book a meeting, read a plan, push a lead. Your credentials, encrypted per workspace; the model never sees them.
Migrate
A one-time import of your existing help content or bot training into the Brain, so Peeve starts from what you already wrote. No re-authoring.
Custom (MCP)
Point Peeve at your own MCP server and it connects as a client, exposing your tools the same way Claude uses a custom MCP.
Custom (API)
Point Peeve at your REST API docs and it builds the connector for you: base URL, auth and every endpoint, each marked read or write.
Support & messaging
Hand-offs and two-way conversations land in the tools you already run.
Email
Send hand-offs from your own mailbox: Gmail, Outlook, or any SMTP.
Slack
Post hand-offs and notifications into a channel.
Zendesk
Create or append a ticket from a hand-off.
Linear
Log a bug as an issue, from a hand-off or automatically when Peeve spots one during a session, with the session attached.
Scheduling
Book meetings straight from the cursor.
Cal.com
Surface availability and book an event type.
Calendly
Share a scheduling link and book.
Payments & subscriptions
Read a customer's plan and act on it.
Stripe
Read a customer's plan and lifecycle; generate a checkout or portal link.
CRM & leads
Read who someone is, and push the leads Peeve captures.
HubSpot
Read a contact's plan and lifecycle; push captured leads.
Salesforce
Read and write leads and contacts.
Migrate your knowledge → the Brain
A one-time import of your existing help content or bot training, so Peeve starts from what you've already written.
Intercom / Fin
Help-center articles and Fin content.
Chatbase
Bot sources and training data.
Tidio / Lyro
Knowledge base and Lyro training.
Crisp
Helpdesk articles.
Freshchat / Freshdesk
Solutions and articles.
Help Scout
Docs articles.
Ada
Bot answers.
Botpress
Flows and knowledge base.
Voiceflow
Conversation flows and knowledge base.
File import
CSV, JSON, or Markdown export.
AI agents (agent channel)
Your users point their own AI agent at a scoped Peeve endpoint and get your capabilities as typed tools, the same permissions they have, never more.
Claude
Add your Peeve endpoint as a custom MCP connector.
OpenAI
Connect via MCP and call your tools with stated effects.
Hermes
Connect the Hermes agent over MCP to your Peeve endpoint.
OpenClaw
Connect the OpenClaw agent over MCP to your Peeve endpoint.
Any MCP client
Any agent that speaks MCP connects and gets your capabilities as typed tools.
Custom backend (MCP & API)
Bring your own tools. Peeve looks up live data and takes action in your systems, with a confirmation step on anything that changes.
Custom MCP server
Peeve initializes, lists, and calls your MCP tools, like Claude's custom MCP. Growth and up.
Custom API connector
Built automatically from your REST API docs: reads live, writes with confirmation. Scale and up.
It does it, not describes it
Wiring a connector? Peeve shows the user, right on the screen.
The cursor moves to the control, highlights it, and states the scope before anything runs, inside your product, in the user's own session.
01Do I have to move off my current helpdesk?
It is your call. Peeve is a full AI product support agent that resolves support requests end to end inside your product, and when one genuinely needs a person it hands off to your team in Peeve Hand-Offs with the full session, so it can be your entire support layer. If you would rather keep the helpdesk you already run, Peeve also syncs the escalation into Zendesk, notifies your team in Slack, email or a webhook, and logs bugs as Linear issues. Either way, ticket volume goes down because Peeve resolves most of it first.
02How do capabilities map to my backend?
Each capability points at one of your own endpoints, defined in peeve.config.json and reviewable in a pull request. The model requests the capability by name; your execution service makes the actual call with your credentials, which the model never sees.
03Do I need to build an integration to use my own REST API?
No. Paste your API docs URL and Peeve builds the connector for you: base URL, authentication and every endpoint, each marked read or write for review. Add your credentials (encrypted per workspace) and the assistant can use it in conversations. It's minutes, not an engineering project, and the connector tracks your docs; you review and toggle it endpoint by endpoint. Available on Scale.
04Can Peeve connect to my own MCP server?
Yes, on Growth and up. Paste your MCP server URL (and a token if it needs one); Peeve does a live handshake, discovers the tools it exposes, and you choose which ones the assistant may use. Reads happen automatically; anything that changes state runs through a confirmation step. It's an advanced option for teams that already run an MCP server. Most customers never need it.
Why teams choose Peeve
Escalations, your way
Your team picks them up in Peeve Hand-Offs, and they also sync into Zendesk, with a Slack, email or webhook notification and a Linear issue for bugs, if you keep those tools. Peeve doesn't replace the tools you already run.
Your backend, your credentials
Capabilities map to your own endpoints in peeve.config.json; the model never sees a token or picks a call.
Fewer tickets, richer ones
In-product resolution cuts volume, and what does escalate arrives with the full session attached.
14-day trial, no cardInstalls in an afternoonRead-only until you widen itKill switch in one commandCancel anytime. No ONE question asked.
The one question we'll ask on the way out: which answer did Peeve get wrong? It is how the Brain learns. And you were never billed for it in the first place.