Kepler hosts the server
There is nothing to install and no local server to run. You add one server URL to your AI client and sign in to Kepler.
Kepler is an AI recruitment CRM for agencies, and it runs a hosted MCP server. Connect Claude or ChatGPT, sign in with your Kepler account, and the AI client can search your candidates and update your records with the permissions you grant.
| Name | Type | Client | Scopes | Last used | Created | Actions |
|---|---|---|---|---|---|---|
| Claude | Signed in | Claude | crm:readcrm:writeactivities:write | 2 hours ago | 4 Nov | Revoke |
| ChatGPT | Signed in | ChatGPT | crm:read | Yesterday | 28 Oct | Revoke |
| Claude Code | Signed in | Claude Code | crm:readpipeline:writelists:write | 3 Nov | 14 Oct | Revoke |
| Codex | Signed in | Codex | crm:readtasks:write | 30 Oct | 14 Oct | Revoke |
There is nothing to install and no local server to run. You add one server URL to your AI client and sign in to Kepler.
At sign-in you tick what the client may do: read, write records, tasks, notes, pipeline and lists. Read alone is a good place to start.
AI client access is on for every Kepler workspace, including trials.
With read access, the AI client can search candidates in plain English across profiles, CVs, notes and call summaries. It can also look up jobs, companies, contacts and applications, count and break down records, read activity history, check your task list, and read the match results already stored for a job.
Using Kepler, who have we spoken to about senior finance roles in Manchester this year?
Who have we got at second interview for the Zurich role?
Find me people who have actually run a payroll migration.
Log a note on this candidate from my call and set a follow-up task for Thursday.
How many open jobs do I own, and which have no applicants yet?
Kepler gives setup steps for Claude on the web and in the desktop app, Claude Code, ChatGPT, Codex and Grok. Your own tools and integrations use Kepler’s public REST API with scoped API keys. AI Chat is the assistant inside Kepler. MCP is an extra way in, for when you are already working in Claude or another AI client.
Administrators see an AI clients tab under Settings → Developers once AI client access is on. If the tab is missing, email support@keplercrm.com. The exact steps for each client are in the help articles for Claude, ChatGPT and Codex, and Grok.
Connect an AI client
Kepler MCP server URL
https://app.keplercrm.com/api/mcpConnections appear below once the client signs in.
In your AI client, add a custom connector or MCP server and enter the Kepler server URL. Claude Code and Codex add it with one command.
Access allowed
Go back to Claude to finish.
The client sends you to the Kepler sign-in. Choose the workspace and the permissions you want the client to have, then approve.
Using Kepler, how many open jobs do I own?
Ask “Using Kepler, how many open jobs do I own?”. If the client answers from memory, say “use the Kepler tools” once.
A connection can never do more than you can do in Kepler yourself.
Kepler works with Claude. Kepler is an AI recruitment CRM for agencies, and it runs a hosted MCP server. You add Kepler to Claude as a custom connector, sign in with your Kepler account, and Claude can then work with your candidates, contacts, companies, jobs and pipeline. The steps are in Use Kepler with Claude. There is also a longer guide to recruitment CRMs that work with Claude and ChatGPT.
Yes. Kepler hosts it at https://app.keplercrm.com/api/mcp, so there is nothing to install and no local server to run. You connect by signing in to Kepler, not with a copied key. AI client access is on for every Kepler workspace, including trials. If administrators do not see an AI clients tab under Settings → Developers, email support@keplercrm.com.
Yes, once Kepler is connected. With read access, ChatGPT can search candidates in plain English across profiles, CVs, notes and call summaries, and look up jobs, companies, contacts and applications. Your ChatGPT account has to be able to add custom MCP servers. Use Kepler with ChatGPT says who can, and gives the steps.
You decide what the connection can do. You choose the permissions at sign-in, your Kepler role still applies, and each connection reaches one workspace. Custom fields marked sensitive are not available through MCP. Every change is recorded on the record’s timeline under your name, via that AI client, and you can revoke a connection at any time. Data returned to an AI client is processed by that client’s provider under your agreement with them, so check your data controls there. The privacy policy has the detail.
An AI client connected through MCP cannot delete records. Kepler’s MCP server has no delete tools. A rejection or a withdrawal is a recorded outcome, and it can be reopened. If a colleague changed a record after the AI client read it, Kepler refuses the update and the client has to read the record again.
CRM software for recruitment agency owners and teams. We set up your workspace, migrate your data and walk you through it.
We will email you within one working day to set up your workspace and agree a time for the walkthrough.
Want a walkthrough sooner? Book a demo