# project-graph-mcp

> Use this tool when you need to optimize AI agent performance on large codebases by reducing token usage and increasing context window size. It enables compact code reading and editing, solving problems related to limited context understanding and inefficient token utilization. The project-graph-mcp tool takes in codebase data as input and outputs optimized, compact code representations.

Canonical page: https://skillsregistry.net/skills/rnd-pro-project-graph-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rnd-pro-project-graph-mcp

## Description

Maximizes AI agent context window by enabling compact code reading and editing, reducing tokens by 40% for deeper codebase understanding.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/l9vopr4dyx)
- **Repository:** <https://github.com/rnd-pro/project-graph-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rnd-pro-project-graph-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rnd-pro-project-graph-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rnd-pro-project-graph-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt