AI Cognitive Nexus
An AI-powered cognitive nexus MCP server built by SimonUTD that creates and manages autonomous AI agent teams for collaborative problem-solving and task execution. The implementation uses the agno framework to orchestrate multiple AI personas with distinct roles, maintaining persistent team configurations, product knowledge bases, and session management through JSON data stores with file locking for concurrent access. Designed for complex workflows requiring multi-agent coordination, it supports various LLM providers (OpenAI-compatible APIs, DeepSeek) and integrates web search capabilities via Exa API, making it suitable for research projects, product development teams, and scenarios where distributed AI reasoning and specialized agent roles can enhance decision-making processes.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/simonutd/ai-cognitive-nexus-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve AI Cognitive Nexus 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.