# Crisp [Health: Active]

**Category:** 🎧 Support & Service Management  
**Repository:** https://github.com/mcp-dir/crisp-mcp  
**GitHub Stars:** 0  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/crisp

## Description
Customer support, live chat, CRM and helpdesk on Crisp with the full official REST API v1 (api.crisp

## Tools
Capabilities this server exposes over MCP:

- **search_tools** — Single entrypoint for MCP catalog. action=search returns available tools ordered by relevance. action=describe returns tool schema. action=invoke executes a tool by ID.
- **show_version** — Show the current MCP platform and adapter versions.
- **report_bug** — Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
- **connect** — Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
- **authenticate** — MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
- **toolkit_info** — Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
- **marketplace** — The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "crisp": {
    "url": "https://api.mcp.ai/p_crisp"
  }
}
```

## Documentation

## What the Crisp MCP server does

Crisp MCP server lets an MCP-compatible client query data from Crisp, a platform for customer support, live chat, CRM, and helpdesk operations. The integration covers the official Crisp REST API v1 at `api.crisp.chat` and is designed for read-only access.

Supported data areas include conversations and messages, contacts or people, knowledge base articles, categories and languages, campaigns, operators, visitors, and website settings. That makes it suitable for questions such as which conversations are open, which contacts arrived recently, or which articles are published.

The repository is a public wrapper containing manifests, documentation, and agent skills. The hosted MCP endpoint is proprietary, while the repository is released under MIT.

## How it works

The Crisp MCP server is accessed through MCP over HTTP. For the hosted deployment, clients connect to:

`https://api.mcp.ai/p_crisp`

Authentication uses a pair of tokens generated in Crisp under Settings, Workspace settings, and Advanced configuration.

A single exposed entry point, `search_tools`, provides access to the MCP catalog. Although the server presents one MCP tool, its documented purpose is to query the supported Crisp REST API areas through that entry point. Returned data is sent to the LLM host selected by the user, such as Claude, ChatGPT, Cursor, or a custom agent.

## Setup and configuration

The hosted endpoint can be added to Claude Web or Claude Desktop through Claude's custom connector settings. Cursor and VS Code have installation links in the project documentation. Other clients can use the same HTTP URL if they support MCP over HTTP.

No environment variable configuration is documented for the hosted service. To connect Crisp data, configure the required Crisp token pair through the applicable authentication flow rather than relying on a local server configuration described in this listing.

## Tools and capabilities

The available MCP tool is:

- `search_tools`: the single entry point for the MCP catalog.

Through the integration, agents can read:

- Crisp conversations and messages
- Contacts and people
- Knowledge base articles, categories, and languages
- Campaigns
- Operators
- Visitors
- Website configuration

It is therefore intended for inspection, lookup, and question answering rather than sending messages, editing contacts, publishing articles, or changing settings.

## Limitations and notes

Access is read-only, so workflows that need to modify Crisp data are outside the stated scope. The hosted MCP service is proprietary even though the public wrapper repository is MIT-licensed.

Crisp data returned by the tools is passed to the LLM host chosen by the user. The project identifies Crisp IM SAS and the selected LLM host as subprocessors and recommends considering plans with training opt-out controls. Review the project's privacy documentation before using the connection with sensitive support or customer data.

The integration is documented for Claude Desktop, Cursor, VS Code, Cline, and Continue, and can also be used with MCP clients that support HTTP transport.

_Full upstream README: https://allmcps.com/mcp/crisp/readme_