Agentic Multi-AI Toolkit
This MCP server implements a pure agentic architecture that organizes functionality into specialized agents (OpenAI, Ollama, and File agents) managed through a centralized tool registry, enabling AI assistants to access both cloud and local AI capabilities alongside comprehensive file operations. Built with Python using asyncio and the Model Context Protocol specification, it provides 14 tools including OpenAI GPT integration for advanced chat and analysis, local Ollama model support for privacy-focused AI operations, and robust file management with read/write/search/directory operations. The implementation features automatic agent registration with availability checking, tool routing through the registry system, stdio transport for Claude Desktop integration, and fallback mechanisms between AI providers, making it valuable for hybrid AI workflows that require both cloud and local model access, file-based data processing, and building AI assistants that need flexible, modular tool access without vendor lock-in.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/adamsalah13/mcp_server_full
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Agentic Multi-AI Toolkit 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.