MCP Instructions Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Instructions Serverload production instructions"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Instructions Server
Shared Claude instructions for teams. Edit instructions.yaml, everyone gets updates.
Quick Start
Option 1: Docker (Recommended)
docker compose up -d
# Server runs at http://localhost:8080/mcpOption 2: Python
# macOS / Linux
./setup.sh
python server.py
# Windows
python -m venv .venv && .venv\Scripts\activate && pip install -r requirements.txt
python server.pyOption 3: Cloud (Railway)
Set environment variables:
MCP_TRANSPORT=streamable-http
PORT=8080Option 4: Azure Container Instances
./deploy.shRequirements: Azure CLI (az) and Docker installed.
The script creates:
Resource Group
Azure Container Registry
Container Instance with public URL
Redeploy after changes:
# Set your ACR name (check Azure portal or use: az acr list -g rg-mcp-server --query "[0].name" -o tsv)
ACR=your-acr-name
# Build, push and restart
az acr login -n $ACR
docker build -t $ACR.azurecr.io/mcp-server:latest .
docker push $ACR.azurecr.io/mcp-server:latest
az container restart -g rg-mcp-server -n mcp-serverUseful commands:
az container logs -g rg-mcp-server -n mcp-server # View logs
az container restart -g rg-mcp-server -n mcp-server # Restart
az group delete -n rg-mcp-server --yes # Delete allRelated MCP server: threadwork
Which Option to Choose?
Mode | Best For | Cost | Latency |
stdio (local Python) | Personal use | Free | ~0ms |
Docker | Local dev/testing | Free | ~10ms |
Railway | Quick deploy | Pay per use | ~100ms+ |
Azure ACI | Team sharing, Azure users | ~$1-2/month | ~100ms+ |
Note: The server only gets called when you invoke a prompt (/team-instructions:production, etc.). Normal Claude messages don't hit the server. Instructions are loaded once into the conversation context.
Connect Claude Code
Create config file:
Global (all projects):
~/.claude/mcp.jsonPer-repo (this project only):
.mcp.jsonin repo root
Remote server (Docker/Railway/Cloud)
{
"mcpServers": {
"team-instructions": {
"type": "streamable-http",
"url": "https://your-server-url/mcp"
}
}
}Local Python (STDIO)
macOS / Linux:
{
"mcpServers": {
"team-instructions": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/server.py"]
}
}
}Windows:
{
"mcpServers": {
"team-instructions": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\server.py"]
}
}
}Environment Variables
Variable | Default | Description |
|
| Transport: |
|
| Server port (for HTTP transports) |
|
| Alternative port variable |
Available Commands
Prompts
Prompt | Description |
| Strict mode with team standards |
| No rules, full freedom |
| Review code with standards |
Tools
Tool | Description |
| List all commands |
| Reload instructions from file |
Resources
Resource | Description |
| Core principles |
| Production guidelines |
| Delivery checklist |
| All sections combined |
Edit Instructions
Edit
instructions.yamlCall
refreshtool (or restart server)Done - all connected clients get updates
Transports
Transport | Use Case | Endpoint |
| Remote/Cloud (recommended) |
|
| Remote/Cloud (legacy) |
|
| Local Python execution | N/A |
Troubleshooting
Issue | Fix |
Server not found | Use absolute paths, check JSON syntax |
Python errors | Need Python 3.10+, run |
Connection refused | Check |
Invalid Host header | Server needs |
Test Server
# Health check (SSE transport only - not available in streamable-http)
curl http://localhost:8080/health
# Test streamable-http endpoint
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'Note: The /health endpoint only exists when using SSE transport. For streamable-http, use the MCP endpoint test above.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Path-scoped team memories, rules and skills for Claude Code, Cursor, Codex and other MCP clients.
Agent personas for Claude. 16 tools, 13 personas, 3 workflows. Zero extra API cost. Free.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceCentrally manages Claude agent definitions, configurations, and custom commands across multiple devices using a SQLite database, eliminating file synchronization conflicts and enabling live updates across all connected Claude sessions.-
- AlicenseNot gradedqualityDmaintenanceA multi-agent collaboration tool for Claude Code that supports hot-swappable role YAML, persistent memory with SQLite and FTS5, and step-level replay in a single-file HTML viewer.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables searching, retrieving, and managing prompts for Claude Code through natural language, with tools for adding, updating, and deleting prompts.MIT
- AlicenseNot gradedqualityAmaintenanceTurns Claude into a career co-pilot that manages resumes, cover letters, job applications, and interview prep using local YAML files.7914MIT