Configure grepai MCP server for Claude Code, Cursor, or Windsurf with scope and workspace options.
Configures grepai MCP servers for AI coding assistants with IDE-specific setup and workspace options.
npx claudepluginhub jugrajsingh/skillgardenThis skill is limited to using the following tools:
Configure grepai as an MCP server for AI coding assistants. Supports multiple IDEs, scopes, and workspace modes.
Check all possible MCP registration locations and grepai config:
# Check existing MCP registrations
claude mcp list 2>/dev/null
Glob: .mcp.json
Glob: .claude/mcp.json
Read: ~/.claude.json (look for mcpServers section)
Check for workspaces:
grepai workspace list 2>/dev/null
Check for local project config:
Glob: .grepai/config.yaml
Summarize findings before proceeding:
which grepaiAsk via AskUserQuestion:
Which IDE to configure?
○ Claude Code (Recommended)
○ Cursor
○ Windsurf
○ Generic .mcp.json
For Claude Code, ask via AskUserQuestion:
Where should the MCP server be registered?
○ Project .mcp.json (Recommended for teams — shareable via git)
○ User global (~/.claude.json — available in all sessions)
○ Project .claude/mcp.json (this project only, not shared)
For Cursor: config goes to .cursor/mcp.json (project-level).
For Windsurf: config goes to .windsurf/mcp.json (project-level).
For Generic: config goes to .mcp.json at project root.
Only ask this if workspaces were detected in step 1.
Ask via AskUserQuestion:
Workspace mode?
○ With --workspace {NAME} (Recommended — auto-searches all projects without extra params)
○ Without workspace (agent must pass workspace parameter manually)
○ No workspace (single project mode)
If workspace selected, show the available workspaces and let user pick:
Which workspace?
○ {ws1} ({N} projects)
○ {ws2} ({N} projects)
Determine the grepai binary path:
which grepai
claude mcp addUser scope:
claude mcp add grepai -s user -- grepai mcp-serve {ARGS}
Project scope:
claude mcp add grepai -s project -- grepai mcp-serve {ARGS}
Where {ARGS} is:
--workspace {NAME}{PROJECT_PATH}.mcp.json (project root, Cursor, Windsurf, Generic)Determine the target file:
.cursor/mcp.json.windsurf/mcp.json.mcp.jsonWrite the JSON config:
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"]
}
}
}
With workspace:
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve", "--workspace", "{NAME}"]
}
}
}
With explicit project path:
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve", "{PROJECT_PATH}"]
}
}
}
If the target JSON file already exists, read it first and merge the grepai key into the existing mcpServers object. Do not overwrite other MCP servers.
mkdir -p .cursor # for Cursor
mkdir -p .windsurf # for Windsurf
For project-level .mcp.json files that teams share, do NOT gitignore them.
For .claude/mcp.json (project-specific, not shared), check if .claude/ is in .gitignore. If not, suggest adding it.
For Claude Code:
claude mcp list
Confirm grepai appears in the list.
For file-based configs:
Read the written file to confirm it's valid JSON.
Note: The MCP server connects on next IDE session start, not immediately.
============================================================================
GrepAI MCP Server Configured
============================================================================
IDE: {IDE}
Scope: {SCOPE}
Config: {FILE_PATH}
Command: grepai mcp-serve {ARGS}
Workspace: {NAME or "none"}
The MCP server will be available in your next {IDE} session.
It exposes these tools:
grepai_search — Semantic code search
grepai_trace_callers — Find all callers of a function
grepai_trace_callees — Find all callees of a function
grepai_trace_graph — Build call graph around a symbol
grepai_index_status — Check index health
{IF WORKSPACE}
Workspace mode is enabled. The agent will automatically search
across all {N} projects in the "{NAME}" workspace without needing
to specify the workspace parameter.
{END IF}
To verify after restart:
claude mcp list # Claude Code
============================================================================
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.