Agent skill
add-mcp
Add an MCP server to the project and sync to all AI tools
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/add-mcp
SKILL.md
Add MCP Server
Add a new MCP server to .mcp.json (the single source of truth) and sync to all AI tool configs.
Steps
-
Parse the arguments:
$ARGUMENTS- Format:
<name> <url>for HTTP servers (e.g.loki http://loki-mcp.ablz.au:8081/stream) - Format:
<name> <command> [args...]for stdio servers (e.g.mcp-nixos uvx mcp-nixos) - If arguments are missing or ambiguous, ask the user.
- Format:
-
Read the current
.mcp.jsonfrom the repo root. -
Add the new server entry:
- For URLs (starts with
http://orhttps://):{"type": "http", "url": "<url>"} - For commands (anything else):
{"command": "<command>", "args": ["<remaining args>"]}
- For URLs (starts with
-
Write the updated
.mcp.json. -
Run the sync script to push to Codex:
python3 .claude/skills/sync-mcp/sync.py -
Report what was added and remind the user to restart Claude Code for the new MCP server to take effect.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?