Manus
ManusMCP is a framework for orchestrating specialized AI agents that work together through a Model Context Protocol (MCP) server implementation. Built with TypeScript, it provides file operations, shell command execution, and browser automation capabilities through a comprehensive API. The server enables AI agents to read/write files, execute shell commands, navigate web pages, and interact with browser elements. The implementation includes a Docker-based deployment with services for Flowise, Unstructured API, and LiteLLM, making it ideal for creating AI team members with specialized roles like Planner, FileWizard, CommandRunner, and WebNavigator that can collaborate on complex tasks requiring filesystem access, command-line operations, and web interactions.
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/mantrakp04/manusmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Manus 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.