SiteList review score
Exceptional local-first positioning for AI developer workflows. Accessibility gaps in functional forms and design system technical debt require attention.
Reviewed on Sep 6, 2026
Codeindexer
codeindexer.dev
Unclaimed listingIs this your site?
Claim itWhat it does
Codeindexer is a local MCP server that provides AI agents like Cursor, Claude Code, and Copilot with deep codebase intelligence. It features a queryable call graph, semantic search, and persistent memory. Supporting 28 languages, it runs entirely offline to ensure code privacy while reducing token costs by providing precise context. It includes 32 tools for search, graph analysis, and security auditing, compatible with any client using the Model Context Protocol standard.
Two ratings
Verified user rating
—
No verified reviews yet — the evidence locker is empty.
Screenshots
Captured during our latest review on Sep 6, 2026
Pricing details
Pro is $20/mo or $16/mo billed annually. Security is $32/mo billed annually. Billed monthly. free plan · Free forever for up to 3 projects.
| Plan | Price | Details |
|---|---|---|
| Free | $0 monthly per 3 projects | Forever, for solo work and side projects. Up to 3 indexed projects · 100,000 chunks total · Symbol, semantic and exact search · 8 active phases · 42 open cards View source |
| Pro | $20 monthly per per seat | Everything serious developers and small teams need. Unlimited projects and chunks · Cascade search · Call graph · Code quality analysis View source |
| Pro (Annual) | $192 annual per per seat | Everything serious developers and small teams need. Unlimited projects and chunks · Cascade search · Call graph · Code quality analysis View source |
| Security (Annual) | $384 annual per per seat | Findings that deserve your attention. One command, your whole repo, signal over noise. Deep audit pipeline · Security disclosure support View source |
Key features
Call Graph
Analysis
Analyzes callers, callees, chains, cycles, and shortest paths in the codebase.
Semantic Search
Search
Embedding-based search to find code by meaning rather than just keywords.
Cascade Search
Search
Smart picker that combines symbol, semantic, and exact search modes.
Persistent Memory
Context
Maintains context and decisions across different AI agent sessions.
Code Quality Analysis
Analysis
Identifies dead code, complexity hotspots, and function rankings.
Cross-file Analysis
Analysis
Bridges execution flows and related files across the entire repository.
32 MCP Tools
Connectivity
Exposes search, graph, memory, and audit tools via the Model Context Protocol.
Who it’s for
Solo Developers
Enhancing AI agents for side projects and daily coding tasks with precise context.
Engineering Organizations
Providing reliability, support, and on-prem control for critical software development.
AI Agents
Giving autonomous agents a deep technical surface and persistent memory of codebases.
Integrations
Cursor
Developer Tools
AI-powered code editor with built-in MCP support.
Claude Code
Developer Tools
Anthropic's command-line AI agent.
Claude Desktop
Developer Tools
Desktop application for Claude with MCP tool capabilities.
VS Code Copilot
Developer Tools
GitHub Copilot extension for Visual Studio Code.
Windsurf
Developer Tools
Agentic IDE with native MCP integration.
OpenAI Codex CLI
Developer Tools
Command-line interface for OpenAI's code models.
Gemini / Antigravity
Developer Tools
Google's AI models and associated agentic tools.
Buyer questions
Questions buyers actually ask
What is MCP, and why does it matter?
Model Context Protocol is an open standard introduced by Anthropic that defines how AI agents talk to external tools. Building on MCP means codeindexer works with whatever AI client you use today — and whatever you switch to tomorrow.
How is this different from Cursor’s built-in indexer?
Cursor's indexer is locked to Cursor and mostly does embedding-based search. codeindexer works with every MCP client, offers semantic + symbolic + exact search in one cascade, walks the real call graph, runs security audits, and gives your agent persistent memory across sessions.
Product FAQ information · View source
The expert review
Codeindexer earns an 86/100 for its highly optimized, privacy-first MCP server designed for developer AI agents. While it excels in technical performance and positioning, it faces minor hurdles in accessibility and design system technical debt.
86/100: High-performance developer tool with minor technical debt
Verified user reviews
0 verifiedNo reviews yet. The evidence locker is empty.
Reviews from verified users appear here once approved.
Reviews are from the SiteList community. Some reviewers received incentives — disclosed in the review, always. The verdict is never for sale.
Scores across 13 dimensions
Brand & experience
Performance
Content & editorial
Trust & decision surfaces
Search & discoverability
Docs & measurement
- Domain
- codeindexer.dev
- Category
- Agent tooling & MCP
- Pricing
- Freemium · $16–$32/mo
- Platforms
- web, desktop, api
- Founded
- 2026
- Last checked
- Sep 6, 2026
- Public dimensions
- 13
Similar tools
Scavio
Score 87 out of 100 — Strongscavio.dev
Scavio is a scraper API for retrieving live, structured JSON data from social, search, ecommerce, jobs, reviews, and real-estate platforms for AI agents and developers.
agent-manager — The fastest workflow for developing with AI
Score 87 out of 100 — Strongagent-manager.dev
A Go terminal UI that runs every AI coding agent as a live tmux session.
Devsnoop
Score 86 out of 100 — Strongdevsnoop.com
DevSnoop is a local Chrome extension and native host that provides coding agents with structured browser inspection, interaction, and debugging capabilities via a local HTTP API on port 9400.
CrewTower — Control your agents from the notch
Score 83 out of 100 — Strongcrewtower.app
Crew Tower turns the MacBook notch into a live control tower for every AI coding agent you run. Approve, deny, answer and jump to the exact terminal tab without leaving what you are doing.