@navop/mcp
MCP stdio bridge to a running Navop desktop application, enabling AI agents to interact with Navop via MCP protocol.
README
Navop JavaScript packages
This repository publishes three focused packages for integrating with a running Navop desktop application:
| Package | Role | Executable |
|---|---|---|
@navop/client |
Shared discovery and authenticated MCP transport | none |
@navop/cli |
Terminal commands and bundled Agent Skill | navop |
@navop/mcp |
MCP stdio bridge | mcp, navop-mcp |
There is no compatibility burden from the former combined package in this baseline release. Keep the layers separate: use the CLI/Skill when an AI Agent should operate Navop through terminal commands, and use the MCP package when an MCP client needs a stdio bridge.
Requirements
- Node.js 20 or newer.
- A running Navop desktop application.
- Settings > General > MCP > MCP Server enabled in Navop.
- The required groups enabled under Settings > General > Tool Exposure.
- Any connection or terminal session required by the selected operation opened in Navop.
CLI and Skill
The Skill keeps a compact workflow in the Agent context. It discovers status, command help, and live schemas only when needed instead of registering the complete MCP tool catalog on every turn. This can reduce repeated context and tool-definition Token overhead; the result depends on the client and exposed tool count. The CLI still uses Navop's authenticated loopback Public MCP runtime, so host-controlled Tool Exposure, permissions, approvals, sessions, results, and auditing remain in force.
npm install -g @navop/cli@latest
navop --help
navop status --json
navop connections list --json
navop tool list --json
navop tool schema <tool-name> --json
navop tool call <tool-name> --arguments '<json-object>' --json
Representative resource commands use IDs returned by Navop:
navop ssh exec --target <ssh-session-id> --command 'uname -a' --json
navop sftp list --connection <ssh-connection-id-or-name> --path /var/log --json
navop redis get --connection-id <redis-connection-id-or-name> --key app:status --json
navop mongo find --connection-id <mongo-session-id> --database app --collection users --filter '{"active":true}' --limit 20 --json
navop db query --connection <database-connection-id-or-name> --sql 'SELECT 1' --json
navop terminal read --target <terminal-session-id> --lines 80 --json
The CLI is a global command. Check the registry and update the installed package when needed:
npm view @navop/cli version
navop --version
npm update -g @navop/cli
navop status --json
MCP bridge
Use @navop/mcp when the consuming client expects an MCP stdio server. The bridge has no domain CLI and emits only MCP JSON-RPC on stdout:
npx -y @navop/mcp@latest --discovery /path/to/navop/public-mcp.json
Host authority
The running Navop host defines the available tools, schemas, annotations, Tool Exposure groups, permission mode, connections, sessions, resource identifiers, results, and business errors. These packages do not carry a static copy of the complete host catalog and do not bypass host security boundaries.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.