Skip to content

mcp-quickstart.md

Latest commit

 

History

History
143 lines (107 loc) · 3.4 KB

mcp-quickstart.md

File metadata and controls

143 lines (107 loc) · 3.4 KB
Raw

MCP Quickstart — Use MisakaNet in Cursor / Claude Desktop / Claude Code

Give your AI coding assistant access to 287 indexed failure-recovery lessons from real debugging sessions.

What you get

When your agent encounters an error, it can search MisakaNet for known fixes before wasting time re-debugging:

You: "My pip install keeps timing out on WSL"
Agent: *searches MisakaNet* → finds pip-install-timeout-ssl lesson → applies fix

Copy this to your coding agent

Paste this into Cursor, Claude Code, or Claude Desktop to install and test MisakaNet in one shot:

Please install and test MisakaNet as an MCP failure-memory server.

1. Clone https://github.com/Ikalus1988/MisakaNet
2. Configure it as an MCP stdio server:
   - Command: python3
   - Args: /path/to/MisakaNet/scripts/mcp_server.py
3. Restart your MCP client (Cursor / Claude Code / Claude Desktop)
4. Run the first query: Search MisakaNet for "database locked"
5. Confirm that misakanet_search returns failure-recovery lessons with title, score, and path.

MisakaNet is a failure-memory and recovery layer for coding agents / MCP clients. Local stdio MCP calls work independently of Glama analytics.

Setup

Claude Code

Add to .claude/settings.json in your project:

{
  "mcpServers": {
    "misakanet": {
      "command": "python3",
      "args": ["/path/to/MisakaNet/scripts/mcp_server.py"]
    }
  }
}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "misakanet": {
      "command": "python3",
      "args": ["/path/to/MisakaNet/scripts/mcp_server.py"]
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "misakanet": {
      "command": "python3",
      "args": ["/path/to/MisakaNet/scripts/mcp_server.py"]
    }
  }
}

Docker / GHCR

No local Python setup needed — pull the container and run:

docker pull ghcr.io/ikalus1988/misakanet:2.15.0
docker run -i ghcr.io/ikalus1988/misakanet:2.15.0

Or use in MCP config:

{
  "mcpServers": {
    "misakanet": {
      "command": "docker",
      "args": ["run", "-i", "ghcr.io/ikalus1988/misakanet:2.15.0"]
    }
  }
}

Prerequisites

cd /path/to/MisakaNet
pip install -r requirements.txt

Smoke test

# Verify the server starts
python3 scripts/mcp_server.py --help

# Test search directly
python3 search_knowledge.py "DCO sign-off"

Demo queries

Once connected, try these in your AI assistant:

Query What you'll find
"Search MisakaNet for DCO sign-off failure" DCO quickfix workflow
"Find lessons about GitHub token issues" PAT, credential helper, auth failures
"What does MisakaNet know about pip timeout?" SSL/proxy timeout fixes
"Search for FANUC error codes" Industrial robot debugging lessons
"Find feishu API integration issues" Feishu/Lark API pitfalls

Troubleshooting

Issue Fix
"No MCP server found" Check path in config is absolute
"Import error" Run pip install -r requirements.txt
"No results" Verify data/lessons.json exists and is valid
Windows encoding error Set PYTHONUTF8=1 or use python3 -X utf8

Learn more