data-ai MCP Server
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt UI dashboard. Also includes an Agentic Team runtime with role-based multi-agent open communication & lead-gated final responses.
Discovered via github-topic:mcp-server and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
`frontend.md`
File
`testing.md`
RELATED_TO, CAUSED_BY, FIXED_BY, SIMILAR_TO, DEPENDS_ON, etc.
Usage relationship (pattern → task)
Resolution link (mistake → fix)
`observability.md`
Reusable task templates across 6 categories
File
General semantic relationship
Causal chain (mistake → root cause)
Derived knowledge (snippet → pattern)
`config.md`
Temporal ordering (later event)
`implementer.toml`
Domain experts for web, backend, security, DevOps, AI/ML, database, mobile, performance, documentation
Count
Dependency relationship
Evolution tracking (v1 pattern → v2)
Similarity link (patterns, tasks)
Cross-reference between nodes
None
Knowledge derivation (preference → conversation)
Count
`database.md`
Gemini<br/>Copilot
LOCAL[Route to Local Adapter<br/>Ollama / llama.cpp] FB -->
Codex --> Gemini --> Claude
Claude --> Gemini
Agent error count
`orchestrator_execute`, `agentic_team_execute`, `list_engines`, `orchestrator_health`, `agentic_team_health`, `list_workflows`, `list_agents`, `validate_config`, `team_config`, `agentic_team_validate`
`dockerfile_analysis`, `compose_analysis`, `ci_config_check`, `deploy_checklist`, `env_config_analysis`
`context-graph-builder`
`performance.md`
`security.md`
Offline"] O_OBS["Observability<br/>Prometheus
EXEC[Execute via Adapter] HEALTH -->
Pipeline
Gemini --> Claude
Description
Agent invocations
Temporal ordering (earlier event)
`explorer.toml`
`react-components`, `rest-api-design`, `python-async`, `database-queries`, `graphql-development`, `error-handling`
`api-documentation`, `architecture-docs`, `code-documentation`
`adapters.md`
Purpose
gemini
How it runs
Codex only
local-code --> local-instruct
Total tasks executed
Cache performance
`suggest_tests`, `test_coverage_analysis`, `parse_tests`, `create_test_stub`
`context_store_conversation`, `context_store_task`, `context_log_mistake`, `context_store_pattern`, `context_search`, `context_get_relevant`, `context_stats`
Orchestrator (`orchestrator/`)
Codex --> Copilot --> Gemini --> Claude --> Gemini
local-code --> Claude (fallback: local-instruct)
Task execution time
Description