What is sgraph-mcp-server CLAUDE.md?

Project instructions for SGraph MCP Server, a Python server that gives AI agents access to cached software structure and dependency graphs. MCP is a standard way for AI tools to call external services.

Use it when developing or operating SGraph MCP Server: install dependencies, start a selected server profile, run security reports, and execute unit, integration, or performance tests.

It provides the commands and conventions needed to install, run, configure, and test this particular server without guessing how the repository is organized.

How softagram/sgraph-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to softagram/sgraph-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/softagram/sgraph-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/softagram/sgraph-mcp-server

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/softagram/sgraph-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/softagram/sgraph-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/softagram/sgraph-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/softagram/sgraph-mcp-server/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/softagram/sgraph-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/softagram/sgraph-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,045 This file is loaded in full into every session.

When invoked 1,045 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01045	$0.01045
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 2mo ago against content hash 656c0cd886fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sgraph-mcp-server CLAUDE.md scanned grade A with 0 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

SGraph MCP Server is a Python 3.13+ MCP (Model Context Protocol) server that provides AI agents with fast access to software structure and dependency information through cached sgraph models. It reduces query time from seconds to milliseconds by pre-loading hierarchical graph models into memory.

Development Commands

# Install dependencies
uv sync

# Run the MCP server (port 8008) - default legacy profile
uv run python -m src.server

# Run with specific profile
uv run python -m src.server --profile claude-code  # 8 optimized tools
uv run python -m src.server --profile legacy       # 14 tools (default)

# Run security audit CLI
uv run python -m src.tools.security_report_cli /path/to/model.xml.zip
uv run python -m src.tools.security_report_cli /path/to/model.xml.zip -o report.md --top-n 20

# Run all tests
uv run python tests/run_all_tests.py

# Run specific test categories
uv run python tests/run_all_tests.py unit
uv run python tests/run_all_tests.py integration
uv run python tests/run_all_tests.py performance

# Run a single test file
uv run python -m pytest tests/unit/test_model_manager.py -v

# Lint with ruff
uv run ruff check src/

Architecture

The project uses a layered modular architecture:

MCP Client Request
       ↓
[Tools Layer] src/tools/        → MCP tool definitions, input validation
       ↓
[Services Layer] src/services/  → Business logic (search, dependencies, overview, security audit)
       ↓
[Core Layer] src/core/          → Model management, data conversion
       ↓
[SGraph Library]                → Graph operations

Key Components

Core (src/core/):

ModelManager - Async model loading with 60s timeout, in-memory caching, nanoid-based model IDs
ElementConverter - SElement to dictionary conversion

Services (src/services/): Static methods for testability

SearchService - Pattern matching (regex/glob), type filtering, scoped searches
DependencyService - Transitive dependency chains, subtree analysis, bulk retrieval
OverviewService - Hierarchical structure generation with configurable depth

Read the full file on GitHub · 117 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.

2mo ago First seen · 117 lines · 1,045 tokens per session scan A 656c0cd886fe

Subscribe to this mod's changes

sgraph-mcp-server CLAUDE.md is an instructions file published in the GitHub repository softagram/sgraph-mcp-server (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,045 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging

sgraph-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sgraph-mcp-server CLAUDE.mdsoftagram/sgraph-mcp-server	Instructions file	4	1mo ago	MIT	A	1,045	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

sgraph-mcp-server: Instructions file for Claude Code