grepai-mcp-cursor

grepai-mcp-cursor is a skill for Claude Code from yoanbernabeu/grepai-skills. It costs 29 tokens per session (1,604 once invoked), scanned B, original, MIT.

A setup guide for connecting GrepAI, a tool for meaning-based code search and dependency navigation, to Cursor, an AI-powered code editor. It configures the connection through MCP, a standard way for AI tools to call external services.

In plain words
What is it for?
Installing prerequisites, indexing a project, configuring Cursor's MCP settings, and checking that Cursor can use GrepAI searches.
Why use it?
It lets Cursor search for related code and dependencies by meaning, even when a simple text search would miss them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code; mentions Cursor.

Part of the grepai-integration plugin — 3 skills shipped together , and of grepai-complete

Good fit Installing prerequisites, indexing a project, configuring Cursor's MCP settings, and checking that Cursor can use GrepAI searches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add yoanbernabeu/grepai-skills --skill grepai-mcp-cursor
Clone the repo
git clone --depth 1 https://github.com/yoanbernabeu/grepai-skills

Made for: Claude Code.

Or install grepai-integration, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for grepai-mcp-cursor

README.md
[![agentmods](https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor/github.svg)](https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor)
Your own site
<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for grepai-mcp-cursor

Your own site · 80×15
<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-mcp-cursor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,604 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk fail 15 Feb 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.01604
Opus 5 $0.00015 $0.00802
Sonnet 5 $0.00006 $0.00321
Haiku 4.5 $0.00003 $0.00160

Measured 11d ago against content hash dfed5c71e443, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

grepai-mcp-cursor scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

1. **Version control:** Add `.cursor/mcp.json` to git (without secrets)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Check Ollama: `curl http://localhost:11434/api/tags`
skills/integration/grepai-mcp-cursor/SKILL.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

{
  "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

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

Per-Project Configuration

For project-specific settings:

{
  "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

Read the full file on GitHub · 311 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 311 lines · 29 tokens per session scan B dfed5c71e443

Subscribe to this mod's changes

grepai-mcp-cursor is a skill published in the GitHub repository yoanbernabeu/grepai-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 1,604 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

codebase-search

Semantic code and documentation search by meaning. Use codebasepeek to find WHERE code is (saves tokens), codebasesearch to see actual code. For exact identifiers, use grep instead. Search local codebase before using websearch for code/library/API/example questions.

Helweg/open-codebase-index · 58 tokens

qdrant-advisor

Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory / OOM crashes, optimizer stuck or slow, indexing slowness, scaling and…

qdrant/skills · 216 tokens

qdrant-search-quality-diagnosis

Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', 'quality dropped after quantization', 'how to measure retrieval quality', 'build a golden…

qdrant/skills · 104 tokens

qdrant-monitoring-debugging

Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.

qdrant/skills · 75 tokens

codebase-search

Preferred local codebase-understanding workflow for Pi and Codex. Start with codebasecontext before shell search or broad reads, then use specialized semantic and graph tools.

Helweg/open-codebase-index · 37 tokens

cocosearch-debugging

Use when debugging an error, unexpected behavior, or tracing how code flows through a system. Guides root cause analysis using CocoSearch semantic and symbol search.

VioletCranberry/coco-search · 37 tokens