AgentIndex icon
AgentIndex
code-graph-mcp logo
code-graph-mcp
★ 85
vs
CodeNib logo
CodeNib
★ 87

code-graph-mcp vs CodeNib

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.; CodeNib: CodeNib is a multi-view data system designed to serve comprehensive repository context to coding agents. It achieves this by incrementally compiling source code into various views (lexical, semantic, structural) and providing agent-native access through APIs and tools.

01

TL;DR

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 →
CodeNib logo
CodeNibCode Assistant · ★ 87

Providing rich, up-to-date code context to AI coding agents for tasks like code completion, generation, or bug fixing.

Read CodeNib full review →
02

Side-by-Side Comparison

Field
code-graph-mcp logocode-graph-mcp
CodeNib logoCodeNib
Category
Code Assistant
Code Assistant
Stars
★ 85
★ 87
License
MIT
Apache-2.0
Install Command
/plugin marketplace add sdsrss/code-graph-mcp && /plugin install code-graph-mcp
pip install codenib && codenib wiki /path/to/repository
Updated
1d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
Code Knowledge Graph, AST Parsing, Semantic Search
Multi-view Data System, Repository Context, Coding Agents
03

Features

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.
CodeNib logoCodeNib
01Incremental compilation for efficient code repository view updates
02Agent-native context serving via various APIs and tools
03Multiple advanced retrieval strategies (BM25, semantic, regex)
04Structural code understanding using SCIP/LSP-backed symbol graphs
05Agent-agnostic context serving through MCP and LSP-shaped tools
04

Use Cases

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.
CodeNib logoCodeNib
↳Providing rich, up-to-date code context to AI coding agents for tasks like code completion, generation, or bug fixing.
↳Local exploration and auditing of code repositories using the integrated Wiki, Ask view, and Dependency Map.
↳Enabling advanced code search (lexical, semantic, structural) within a repository for developers and researchers.
↳Evaluation and benchmarking of retrieval, navigation, and context policies for AI and software engineering research.
FAQ

FAQ

What is the difference between code-graph-mcp and CodeNib?
Both code-graph-mcp and CodeNib are in the Code Assistant category. code-graph-mcp has 85 stars, while CodeNib has 87 stars.
Which is better, code-graph-mcp or CodeNib?
The best choice depends on your use case. Choose code-graph-mcp if Perform impact analysis to understand the consequences and blast radius of proposed code changes., and CodeNib if Providing rich, up-to-date code context to AI coding agents for tasks like code completion, generation, or bug fixing..
Is code-graph-mcp free or open source?
Yes, code-graph-mcp is open source on GitHub (MIT).
Is CodeNib free or open source?
Yes, CodeNib is open source on GitHub (Apache-2.0).
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 code-graph-mcp →Alternatives to CodeNib →code-graph-mcp details →CodeNib details →