Tribal
@tribal-memory
About Tribal
Tribal captures the engineering knowledge that does not get written down in code or tickets. The reasoning behind a load-bearing decision, the heuristic someone keeps reaching for, the breakthrough that closed a gnarly bug.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tribal": {
"url": "http://127.0.0.1:8725/mcp"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Tribal?
Tribal is an MCP server that captures engineering knowledge not written down in code or tickets — the reasoning behind decisions, useful heuristics, and breakthroughs that closed bugs. It ingests text on demand and exposes a graph of items connected by what they support, contradict, or refine.
How to use Tribal?
Install the skills with npx skills add tribal-memory/skills, then ask your agent to set up Tribal. Visit tribal.build for detailed installation instructions.
Key features of Tribal
- Semantic compression of project knowledge
- Ingests text on demand
- Exposes a graph of connected items
- Items linked by support, contradiction, or refinement
- Designed to work with agent harnesses via MCP
Use cases of Tribal
- Capturing the rationale behind a load-bearing decision
- Preserving a heuristic someone reaches for repeatedly
- Recording the breakthrough that closed a gnarly bug
- Retaining useful knowledge when work is complete
FAQ from Tribal
—
More Other MCP servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Blender
ahujasidOpen-source MCP to use Blender with any LLM
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Comments