About Crewhu
Crewhu MCP server for organizations using its customer feedback, employee engagement, and gamification platform. It lets AI assistants work with surveys, badges, prizes, and user engagement data.
Key features
- 01Manage customer satisfaction surveys
- 02Manage and award employee badges
- 03Manage prize catalogs and redemptions
- 04Access user engagement data
Use cases
- 01Create or manage customer surveys
- 02Award badges as part of employee recognition
- 03Review prize catalog and redemption activity
MCP support
Connects MCP-compatible AI clients to a Crewhu environment and exposes tools for surveys, badges, prizes, and user engagement. Supports stdio and HTTP transports.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
docker run -i --rm -e CREWHU_API_TOKEN -e MCP_TRANSPORT -e AUTH_MODE -e LOG_LEVEL ghcr.io/wyre-ai/crewhu-mcp:v2.0.5CREWHU_API_TOKENSecretCrewhu API token (Settings → Integrations → API)MCP_TRANSPORTTransport mode for the server. Set to 'stdio' for local CLI use; the image defaults to 'http' for gateway hosting.AUTH_MODESecretCredential source: 'env' reads vars locally, 'gateway' expects header injection from the WYRE MCP Gateway.LOG_LEVELLog verbosity: debug, info, warn, errorLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
ghcr.io/wyre-ai/crewhu-mcp:v2.0.5stdioTools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECrewhu MCP Server
A Model Context Protocol (MCP) server for Crewhu — customer feedback, employee engagement, and gamification platform. Enables AI assistants to manage surveys, badges, prizes, and user engagement data.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Crewhu environment.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack. Built by MSPs, for MSPs.
Installation
npm install @wyre-ai/crewhu-mcp
Configuration
Copy .env.example and set the variables below. Leave CONDUIT_S2S_SECRET empty in that file.
| Variable | Required | Description |
|---|---|---|
CREWHU_API_TOKEN | For stdio and AUTH_MODE=env | Crewhu API token. Not read in gateway mode. |
MCP_TRANSPORT | No | stdio (default) or http |
AUTH_MODE | No | gateway (Docker image and Compose default) or env. Gateway mode requires X-Crewhu-Api-Token on each /mcp request and never falls back to CREWHU_API_TOKEN. env uses that variable only after S2S auth succeeds. |
CONDUIT_S2S_SECRET | Yes for HTTP | Service-to-service HMAC secret. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder (changeme, replace-with-a-real-secret, and similar). Compose will not start without it. Generate with openssl rand -hex 32. Never commit a real value. The value is never logged. |
MCP_ALLOW_INSECURE_DEV | No | Set to exactly 1 only for local development to start HTTP without CONDUIT_S2S_SECRET. The process logs a warning and does not enforce X-Gateway-S2S. The listener is forced to 127.0.0.1 even if MCP_HTTP_HOST is a wider address. A placeholder secret is still refused. |
MCP_HTTP_HOST | No | Bind address when MCP_TRANSPORT=http. Defaults to 127.0.0.1. Honored when CONDUIT_S2S_SECRET is set. The container image sets 0.0.0.0. |
MCP_HTTP_PORT | No | HTTP port. Defaults to 8080. |
/health stays unauthenticated and does not require X-Gateway-S2S. The stdio transport does not use CONDUIT_S2S_SECRET.
HTTP authentication
With MCP_TRANSPORT=http and a real CONDUIT_S2S_SECRET, every /mcp request must include X-Gateway-S2S. A missing or invalid header returns 401 before any vendor credential is read.
The header is an HMAC proof:
X-Gateway-S2S: t=<unix seconds>,v1=<hex hmac-sha256>
v1 is the hex-encoded HMAC-SHA256 of the ASCII string t=<unix seconds> (the same t= prefix and value), keyed with CONDUIT_S2S_SECRET. The timestamp must be within 300 seconds of the server clock.
t=$(date +%s)
sig=$(printf 't=%s' "$t" | openssl dgst -sha256 -hmac "$CONDUIT_S2S_SECRET" -hex | awk '{print $NF}')
curl -sS "http://127.0.0.1:8080/mcp" \
-H "X-Gateway-S2S: t=${t},v1=${sig}" \
-H "X-Crewhu-Api-Token: $CREWHU_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
In AUTH_MODE=gateway, /mcp also requires X-Crewhu-Api-Token. A missing or blank header returns 401 and does not fall back to CREWHU_API_TOKEN.
Usage
Running with Claude Desktop
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"crewhu-mcp": {
"command": "npx",
"args": ["@wyre-ai/crewhu-mcp"],
"env": {
"CREWHU_API_TOKEN": "your-crewhu-api-token"
}
}
}
}
Running with Claude Code (CLI)
claude mcp add crewhu-mcp \
-e CREWHU_API_TOKEN=your-value \
-- npx -y @wyre-ai/crewhu-mcp
Docker
The image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass a real S2S secret. In gateway mode, the Crewhu token arrives on each request as X-Crewhu-Api-Token; it is not read from the environment. Startup exits if CONDUIT_S2S_SECRET is empty or a known placeholder.
docker build -t crewhu-mcp .
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-p 127.0.0.1:8080:8080 \
crewhu-mcp
Compose refuses to start when CONDUIT_S2S_SECRET is unset, defaults AUTH_MODE to gateway, publishes 127.0.0.1:8080:8080, and does not set CREWHU_API_TOKEN:
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose up
Single-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses CREWHU_API_TOKEN:
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTH_MODE=env \
-e CREWHU_API_TOKEN=your-value \
-p 127.0.0.1:8080:8080 \
crewhu-mcp
Local HTTP without a secret is development-only. It binds 127.0.0.1 only and logs a warning. A non-loopback MCP_HTTP_HOST is ignored:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm start
Available Domains
Badges
Manage and award employee badges
Prizes
Manage prize catalog and redemptions
Surveys
Create and manage customer satisfaction surveys
Users
User management and engagement data
Development
# Clone the repository
git clone https://github.com/WYRE-AI/crewhu-mcp.git
cd crewhu-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
Contributing
Contributions are welcome! Please see CONTRIBUTING.md if present, or open an issue to discuss changes.
License
Licensed under the Apache License, Version 2.0. See LICENSE for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.