grepai-mcp-cursor
Integrate GrepAI with Cursor IDE via MCP. Use this skill to enable semantic code search in Cursor.
What this skill does
# GrepAI MCP Integration with Cursor
This skill covers integrating GrepAI with Cursor IDE using the Model Context Protocol (MCP).
## When to Use This Skill
- Setting up GrepAI in Cursor
- Enabling semantic search for Cursor AI
- Configuring MCP for Cursor
- Troubleshooting Cursor integration
## What is Cursor?
Cursor is an AI-powered IDE that supports MCP for external tools. GrepAI integration gives Cursor's AI:
- Semantic code search beyond simple text matching
- Call graph analysis for understanding dependencies
- Index-based code navigation
## Prerequisites
1. GrepAI installed
2. Ollama running (or other embedding provider)
3. Project indexed (`grepai watch`)
4. Cursor IDE installed
## Configuration
### Step 1: Create MCP Config File
Create `.cursor/mcp.json` in your project root:
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"]
}
}
}
```
### Step 2: Restart Cursor
Close and reopen Cursor for the config to take effect.
### Step 3: Verify
Ask Cursor's AI:
> "Search the codebase for authentication"
Cursor should use the `grepai_search` tool.
## Global Configuration
For GrepAI in all Cursor projects, use global config:
### Location
- **macOS:** `~/.cursor/mcp.json`
- **Linux:** `~/.cursor/mcp.json`
- **Windows:** `%APPDATA%\Cursor\mcp.json`
### Content
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"]
}
}
}
```
## Per-Project Configuration
For project-specific settings:
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"],
"cwd": "/absolute/path/to/project"
}
}
}
```
## Available Tools
Once configured, Cursor has access to:
| Tool | Description |
|------|-------------|
| `grepai_search` | Semantic code search |
| `grepai_trace_callers` | Find function callers |
| `grepai_trace_callees` | Find function callees |
| `grepai_trace_graph` | Build call graphs |
| `grepai_index_status` | Check index health |
## Usage Examples
### Finding Code
Ask Cursor:
> "Find code that handles user login"
Cursor uses `grepai_search` to find semantically related code.
### Understanding Dependencies
Ask Cursor:
> "What functions call validateToken?"
Cursor uses `grepai_trace_callers` to show all callers.
### Code Navigation
Ask Cursor:
> "Show me the call graph for processPayment"
Cursor uses `grepai_trace_graph` to display dependencies.
## Cursor Settings Integration
### Enable MCP in Settings
1. Open Cursor Settings (`Cmd+,` / `Ctrl+,`)
2. Search for "MCP"
3. Ensure MCP is enabled
### Verify MCP Status
1. Open Command Palette (`Cmd+Shift+P` / `Ctrl+Shift+P`)
2. Search "MCP"
3. Check connected servers
## Windsurf Configuration
Windsurf uses the same MCP format as Cursor:
### Location
Create `.windsurf/mcp.json`:
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"]
}
}
}
```
## Multiple Projects Setup
### Option 1: Separate Configs
Each project has its own `.cursor/mcp.json` with appropriate `cwd`.
### Option 2: Workspaces
```bash
# Create workspace
grepai workspace create dev
grepai workspace add dev /path/to/project1
grepai workspace add dev /path/to/project2
```
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve", "--workspace", "dev"]
}
}
}
```
## Environment Variables
If GrepAI uses environment variables (like API keys):
```json
{
"mcpServers": {
"grepai": {
"command": "grepai",
"args": ["mcp-serve"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}
```
**Better:** Set environment variables in your shell profile instead.
## Troubleshooting
### MCP Not Recognized
❌ **Problem:** Cursor doesn't see GrepAI tools
✅ **Solutions:**
1. Check file location: `.cursor/mcp.json` in project root
2. Verify JSON syntax (no trailing commas)
3. Restart Cursor completely
4. Check `grepai` is in PATH
### Search Returns Nothing
❌ **Problem:** Empty search results
✅ **Solutions:**
1. Ensure index exists: `grepai status`
2. Run `grepai watch` first
3. Verify working directory
### Connection Errors
❌ **Problem:** MCP connection failed
✅ **Solutions:**
1. Test manually: `grepai mcp-serve`
2. Check Ollama: `curl http://localhost:11434/api/tags`
3. Look at Cursor's developer console for errors
### Wrong Results
❌ **Problem:** Results from wrong project
✅ **Solutions:**
1. Set explicit `cwd` in config
2. Check you opened the right folder in Cursor
3. Use `grepai_index_status` to verify
## Performance Tips
1. **Background daemon:** Keep `grepai watch --background` running
2. **Use compact mode:** MCP tools use compact by default
3. **Limit results:** AI will request appropriate limits
4. **Index regularly:** Especially after git pull
## Comparison: Cursor vs Claude Code
| Feature | Cursor | Claude Code |
|---------|--------|-------------|
| Config location | `.cursor/mcp.json` | `~/.claude/mcp.json` |
| Setup command | Manual JSON | `claude mcp add` |
| Project scope | Per-project or global | Global |
| IDE integration | Native | Terminal |
## Best Practices
1. **Version control:** Add `.cursor/mcp.json` to git (without secrets)
2. **Team setup:** Document MCP config in README
3. **Keep index fresh:** Run watch daemon
4. **Test locally:** Verify `grepai mcp-serve` works first
5. **Use workspaces:** For multi-project setups
## Removing Integration
Delete `.cursor/mcp.json` and restart Cursor.
Or remove just GrepAI:
```json
{
"mcpServers": {
// Remove grepai entry
}
}
```
## Output Format
Successful Cursor setup:
```
✅ GrepAI MCP Integration for Cursor
Config: .cursor/mcp.json
Server: grepai mcp-serve
Status: Ready
Available tools:
- grepai_search
- grepai_trace_callers
- grepai_trace_callees
- grepai_trace_graph
- grepai_index_status
Cursor AI can now search your code semantically!
Test: Ask Cursor "search for authentication code"
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.