MCP for Crisp

MCP built for Crisp. Read every chat, email and social thread from Claude, ChatGPT or Gemini — see what people ask all day, how long they wait, and who hinted they were leaving. Comes with 149 skills built in.

Try it now
Works with
Ask Claude to run a skill on Crisp…

Crisp MCP server. Crisp published a demo MCP server itself, and there are community ones. All of them wrap the conversation API; none answers a customer-operations question. Rulebase reads the conversations themselves — connect Crisp and ask Claude, ChatGPT, Gemini or Cursor a question that needs what was actually said, with 149 customer-operations skills carrying the method.

DemandName why customers message you, in causes you can removeDesign, rebuild, or audit a support contact taxonomy — the categories that record why customers contact.
ChatsCatch customers telling you they will leaveHoursDesign the cover your after-hours volume needsHelpdeskFollow search to article to chat, and fix the drop
01QA scorecard designBuild a scorecard, size the sample, keep auto-fails separateAll providersScorecards and calibration02Volume forecastingForecast contacts, and work out how many people you needAll providersDemand and capacity03Routing auditFind misroutes, ping-pong and queues nobody ownsAll providersRouting and backlog04Backlog triageFind the tickets in the backlog actually at riskAll providersRouting and backlog05Bot deflection analysisCheck whether the bot actually reduced contactsAll providersChannels and experience06Handle time analysisFind where handling time goes before anyone blames a personAll providersRouting and backlog07Repeat contact and FCRMeasure repeat contact properly, then FCR from itAll providersRouting and backlog08Cost to serveWork out what a contact really costs, defensiblyAll providersCost and content09Reviewer calibrationSee whether your reviewers agree, and fix bias and noise apartAll providersScorecards and calibration10CSAT and NPS surveysPick between CSAT, NPS and CES, and fix response biasAll providersChannels and experience11AI agent evaluationTest an AI agent before shipping a prompt or model changeAll providersAI oversight12Customer issue researchName why customers contact you, in causes you can removeAll providersDemand and capacity

Crisp and MCP

Is there an MCP server for Crisp?
Yes. Crisp published a demo server on its own GitHub to show how MCP works against Crisp, and there are community servers that search conversations and read transcripts. All of them wrap the conversation API. Rulebase is a different thing: it syncs chats, emails and social threads into one normalised record you can sample, join across channels and measure, with 149 customer-operations skills on top.
Does it handle chat, email and social in one place?
Yes, and that is the point of the conversation schema skill — a customer who asked in chat and followed up by email counts once, not twice.
We are a small team. Is this overkill?
The library is free to install and vendor-neutral, so start there. The MCP server matters once you have enough history that reading it by hand stops being realistic.

The other MCP servers for Crisp

  • crisp-mcp-demo

    From the vendorby Crisp

    Crisp's own reference implementation, published to show how to build MCP against Crisp. A demo rather than a product.

  • crisp-mcp-server

    Communityby platmart

    Search conversations, read chat transcripts and look up contacts from an AI client.

  • crisp-mcp

    Communityby zernio-dev

    Manage conversations, messages and operators from Claude Code.

Use one of these if you want to read or update Crisp records from an AI client — that is what they are for. Rulebase is for the questions they cannot answer: whether the bot is deflecting or merely containing, whether your reviewers agree, whether a complaint was identified, whether first contact resolution is real. Those need the conversation rather than the recorded fields, joined across channels so one customer counts once, in enough volume to sample defensibly.

How to connect Crisp to Claude, ChatGPT or Gemini

  1. Sync Crisp into Rulebase. Connect Crisp to a Rulebase workspace. Rulebase reads a copy of the conversation record; Crisp stays the system of record.
  2. Add the Rulebase MCP server to your AI client. Point Claude, ChatGPT, Gemini or Cursor at the Rulebase MCP server. The conversations, calls and transcripts become readable from the client you already use.
  3. Install the skills and ask. Run npx rulebase-skills install --all, then ask a question. The matching skill runs against your Crisp conversations and answers from what was actually said.

Other platforms: MCP for Zendesk, MCP for Freshdesk, MCP for Help Scout, MCP for Aircall, MCP for Five9, MCP for Genesys Cloud CX, MCP for NICE CXone, MCP for Avaya. Browse all 149 skills. Last reviewed 2026-08-10 · see which platforms publish an MCP server.

Compliance and security
guardrails built in.

SOC 2 Type II. GDPR. PCI DSS. Zero AI training on your data. Built for the compliance demands of regulated financial services.

Read more

SOC Type 2

We meet SOC 2 requirements to ensure secure and compliant management of data across all our systems.

GDPR

With our operations in Ireland, we operate under GDPR – the world's strictest standard for data privacy.

PCI DSS

We protect cardholder and payment data in line with PCI DSS standards, ensuring secure processing across all transactions.

Encryption

We encrypt your data with AES-256 at rest and TLS in transit, ensuring end-to-end protection for every byte.

Review every conversation. Act on what it finds.

AI for customer operations, built for financial services. Specialist agents chase every issue to resolution and every stalled customer to activation.

Rulebase dashboard