How to add MCP servers to Claude Code from the terminal — the claude mcp add command, project vs user scope, and how to confirm the server connected.
Configuring Claude Code
Config file: .mcp.json / ~/.claude.json
Project (shared) path.mcp.json in your project root
Configuration snippet
# Add a server from the terminal
claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/dir
# List configured servers and their status
claude mcp list
Step-by-step Installation Guide
1
Add the server with the CLI
Run "claude mcp add <name> -- <command> [args...]". Everything after the -- is the command Claude Code runs to launch the server. Use -e KEY=value to pass environment variables.
2
Choose a scope
Add --scope project to write the server into a shared .mcp.json your team commits, or --scope user to make it available across all your projects. Local scope (the default) keeps it to the current project for just you.
3
Verify the connection
Run "claude mcp list" to see each server and whether it connected. You can also use the /mcp command inside a Claude Code session to inspect available servers and tools.
Verified ListingOwnership or active status confirmed on AllMCPs.
The official MCP server for AllMCPs.com - submit and manage tools directly from your AI. The open directory for MCP servers. Connect Claude, Cursor, Windsurf, and AI agents to databases, tools, files, and APIs. Explore 10,000+ servers. AllMCPs is the premier, open directory for discovering, evaluating, and installing Model Context Protocol (MCP) servers to equip AI agents and LLMs with real-world superpowers.
Verified ListingOwnership or active status confirmed on AllMCPs.
Scan/purge hidden text & score web domains: TLS, DNS, headers, speed. Free scans, $0.01 actions.The Tools:
text_scan_v1 — free
Scans a text string for invisible Unicode characters, homoglyphs, and normalization issues. Returns a risk score, a list of flagged characters, and detected homoglyphs. Never modifies the input text.
text_purge_v1 — $0.01 per call
Removes invisible Unicode characters and replaces homoglyphs in a text string, then normalizes the result. Returns the cleaned text plus a before-and-after risk comparison.
domain_check_score_v1 — free
Overall score, per-category scores, and how many findings each category raised. Use it to triage: rank a list of domains, confirm one is healthy, or decide whether the full report is worth pulling. It tells you which categories are weak and how many issues they hold, but not what the issues are.
domain_check_score_batch_v1 — free
The same triage scores for up to 100 domains in a single call. One score summary per distinct domain: overall score, per-category scores, and how many findings each category raised. Never the findings themselves.
domain_check_v1 — $0.01 per call
Full report for one domain: weighted score out of 100, per-category breakdown, and every individual finding with a prioritised remediation order.
domain_check_batch_v1 — from $0.005 per domain
The same full report for up to 100 domains in a single call, with one payment for the whole batch instead of one per domain. Both cheaper per domain and much faster than calling domain_check_v1 in a loop.
Verified ListingOwnership or active status confirmed on AllMCPs.
Official Vocuno plugin for Claude that connects to Vocuno's remote MCP server for AI song generation, covers, remixes, stem separation, voice conversion, audio editing, mixing, mastering, and music analysis.
AI 3D model generation and post-processing: text/image/multiview-to-3D via Tripo, plus retopology, format conversion (GLB/FBX/OBJ/STL/USDZ), and stylization. Single Go binary, 10 tools, async generation with polling.
Turn product pages and creative briefs into finished video and image ads from your AI chat.
25 12
Frequently Asked Questions
Use the terminal: claude mcp add <name> -- <command> [args...]. For example, claude mcp add github -- npx -y @modelcontextprotocol/server-github. Add -e KEY=value for secrets and --scope project or user to control where it is stored.