AgentIndex icon
AgentIndex
world-model-mcp logo
world-model-mcp
★ 24
vs
code-graph-mcp logo
code-graph-mcp
★ 85

world-model-mcp vs code-graph-mcp

world-model-mcp: World Model MCP is a temporal knowledge graph designed to provide long-term memory and context for AI coding agents. It prevents hallucinations, stops repeated mistakes, and reduces regressions by validating code changes against learned constraints and re-injecting relevant context.; code-graph-mcp: code-graph-mcp is a high-performance server that builds a structured knowledge graph of your codebase for AI coding assistants. It offers multi-language AST parsing, semantic search, call graph traversal, and HTTP route tracing to provide deep code understanding and optimize LLM context usage.

01

TL;DR

world-model-mcp logo
world-model-mcpCode Assistant · ★ 24

Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality.

Read world-model-mcp full review →
code-graph-mcp logo
code-graph-mcpCode Assistant · ★ 85

Perform impact analysis to understand the consequences and blast radius of proposed code changes.

Read code-graph-mcp full review →
02

Side-by-Side Comparison

Field
world-model-mcp logoworld-model-mcp
code-graph-mcp logocode-graph-mcp
Category
Code Assistant
Code Assistant
Stars
★ 24
★ 85
License
MIT
MIT
Install Command
pip install world-model-mcp && cd /path/to/your/project && python -m world_model_server.cli setup
/plugin marketplace add sdsrss/code-graph-mcp && /plugin install code-graph-mcp
Updated
1mo ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agent Memory, Temporal Knowledge Graph, Code Validation
Code Knowledge Graph, AST Parsing, Semantic Search
03

Features

world-model-mcp logoworld-model-mcp
01Prevent Hallucinations: Validates API/function references against known entities before use.
02Stop Repeated Mistakes: Learns constraints from corrections and applies them in future sessions.
03Reduce Regressions: Tracks bug fixes and warns when changes touch critical regions.
04Survive Compaction: Re-injects top constraints and recent facts after the agent's context window resets.
05Resolve Contradictions: Picks a winner between conflicting facts using confidence, recency, or source count.
code-graph-mcp logocode-graph-mcp
01Multi-language AST parsing across various depths (calls, imports, inheritance, HTTP routes) for languages like TypeScript, Python, Go, Rust, and Java.
02Hybrid semantic code search combining BM25 full-text and vector similarity search with Reciprocal Rank Fusion (RRF).
03Advanced code graph analysis including recursive call graph traversal, HTTP route tracing, dead code detection, and impact analysis.
04Incremental indexing with real-time updates via Merkle tree change detection and LLM context optimization through token-aware snippet extraction.
04

Use Cases

world-model-mcp logoworld-model-mcp
↳Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality.
↳Automate code validation and linting based on project-specific rules and learned patterns, reducing developer effort in code review.
↳Prevent the re-introduction of previously fixed bugs and enforce architectural constraints across development sessions.
↳Manage and track factual information about a codebase over time, enabling temporal queries and evidence-based reasoning.
↳Deploy self-hosted memory for agents in cloud environments (e.g., Claude Managed Agents) using HTTP transport.
code-graph-mcp logocode-graph-mcp
↳Perform impact analysis to understand the consequences and blast radius of proposed code changes.
↳Trace transitive call chains to understand complex function flows and dependencies across your codebase.
↳Conduct semantic searches to find relevant code based on conceptual descriptions, even if exact keywords are not present.
↳Gain a comprehensive overview of project architecture, modules, dependencies, and entry points.
FAQ

FAQ

What is the difference between world-model-mcp and code-graph-mcp?
Both world-model-mcp and code-graph-mcp are in the Code Assistant category. world-model-mcp has 24 stars, while code-graph-mcp has 85 stars.
Which is better, world-model-mcp or code-graph-mcp?
The best choice depends on your use case. Choose world-model-mcp if Enhance AI coding agents (like Claude Code, Cursor, Continue) with a persistent, harness-neutral memory layer to improve code quality., and code-graph-mcp if Perform impact analysis to understand the consequences and blast radius of proposed code changes..
Is world-model-mcp free or open source?
Yes, world-model-mcp is open source on GitHub (MIT).
Is code-graph-mcp free or open source?
Yes, code-graph-mcp is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to world-model-mcp →Alternatives to code-graph-mcp →world-model-mcp details →code-graph-mcp details →