Tribal (Error Knowledge Base)
Tribal is an MCP server implementation for error knowledge tracking and retrieval, providing both REST API and native MCP interfaces for integration with tools like Claude Code and Cline. Developed by Troy Molander at Agentience.ai, it uses ChromaDB for vector similarity search to help AI assistants remember and learn from programming errors, storing error contexts with solutions and finding similar errors via semantic search. The server features JWT authentication, local and cloud storage options, and Docker deployment capabilities, making it ideal for development teams wanting to build a shared knowledge base of programming errors and solutions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/agentience/tribal_mcp_server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Tribal (Error Knowledge Base) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.