Files
agent-skills/skills/mcp-server-setup/metadata.json
T
Epictetus 5f917f4121 Add Publisher v2 + 5 extracted skills
Publisher fixes:
- Checkout new branch before push (was pushing main ref)
- Verify files staged before commit
- Handle duplicate files gracefully
- Clean error reporting per stage

Skills merged to main:
- mcp-server-setup (from pipeshub-ai)
- research-pipeline (from Blacknode)
- multi-agent-sequential-workflow (from Fast-LLM-Agent-MCP)
- unifai-workflow-execution (from UnifAI)
- code-review-agent-workflow (from AgentKit)
2026-08-05 15:15:09 +00:00

29 lines
1.3 KiB
JSON

{
"name": "mcp-server-setup",
"version": "1.0.0",
"goal": "Set up an MCP server to integrate PipesHub with any MCP-compatible client.",
"inputs": [
"MCP server configuration details",
"PipesHub credentials"
],
"steps": [
"Step 1: Clone the `pipeshub-ai/mcp-server` repository using `git clone https://github.com/pipeshub-ai/mcp-server.git`",
"Step 2: Navigate to the cloned directory with `cd mcp-server`",
"Step 3: Run the interactive installer by executing `./install.sh`",
"Step 4: Follow the prompts in the installer to configure the server, including setting up graph DB, message broker, and KV store",
"Step 5: The installer will generate a `.env` file with necessary environment variables. Ensure these are correctly set",
"Step 6: Start the MCP server by running `docker-compose up -d`"
],
"outputs": [
"Running MCP server",
".env file generated"
],
"failure_modes": [
"Installer fails to run due to missing dependencies or incorrect configuration",
"Docker Compose setup issues preventing server from starting"
],
"confidence": 0.95,
"explanation": "This workflow is specific but can be adapted for different deployment environments and configurations.",
"source_repo": "https://github.com/pipeshub-ai/pipeshub-ai.git",
"score": 1.0
}