Connect your code
01
Point it at a repo. Walk away.
Authorize GitHub, pick the repos. Maguyva starts building a ranked map of every symbol, dependency, and import chain in the cloud — not on your laptop.
now in public beta
The codebase context layer for AI coding agents.
One MCP integration gives AI coding agents a grounded map of your repo, before the first edit.
5 fused retrieval modes (semantic, AST, symbol, dependency, and text), ranked into one answer. 11 MCP tools across 278 languages. Priced per workspace, not per seat.
free plan: 3 repos, 50K indexed lines, no card.
24 documented MCP clients file paths + line numbers in every answer
maguyva
questionevidence
Questionplain language
What code handles login and session expiry?
auto → semantic + graph + text
Grounded answercode evidence
Login requests flow through the sign-in route, the shared auth gate, and the session expiry window that decides when access rolls over.
3 grounded hitsranked by signal
semantichandle_login
async def handle_login(request):token = await create_session(request.user)
src/routes/login.py:18
graphAuthGate· auth.py
structuralSessionWindow· session.py
Real coverage
278 languages
Real extraction across the long tail.
One integration
11 MCP tools
Search, symbols, graph, and text in one surface.
Any client
Remote MCP
Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, and other MCP-compatible clients.
Search modes
5 modalities
See what an edit touches before it happens.
What your agent should see
Four ways to see what matters
before the edit starts.
Dependency, type, data-flow, and control-flow context help your agent understand the codebase more accurately before it changes code.
access_check CALL verify_login
api_router IMPORT access_check
Dependency—Change one thing, see everything it breaks.
What happens
You connect GitHub. Maguyva builds the context.
The loop is simple: connect GitHub, let the cloud pipelines keep the repo fresh, connect an MCP client with your API key, and give the agent grounded tools before it edits.
githubcloud pipelinesremote mcp11 tools
We build the map
02
Push code. The index catches up.
Push to GitHub and Maguyva syncs automatically. Code is re-parsed in real time; graph and ranking layers rebuild on a schedule (hourly on paid plans, daily on free). You never run a local indexer.
Plug in where you work
03
One MCP config. Any client.
Drop an API key into Claude Code, Cursor, VS Code, Windsurf, Codex, or whatever ships next week. A few lines of config and you’re up and running.
Agent verifies first
04
11 tools. Fewer hallucinated edits.
Your agent can ask a plain-language question and get ranked results from 5 search modalities, trace the blast radius of a change, find every class inheriting from Exception, or look up a symbol’s PageRank — before it touches a line of code.
What the agent gets back
Grounded context instead of one generic search box.
Not full-text search wearing a trenchcoat.
Semantic, structural, graph, and text retrieval fused in one surface. Your agent gets ranked results, not a wall of grep output.
The important symbols surface first.
Graph-ranked results. The helpers stay buried until you need them.
278 languages. Even COBOL. (Please don't have COBOL.)
Custom AST queries per language, not one regex pretending it understands Haskell.
Know what breaks before you break it.
Trace dependents, find orphaned code, and let your agent kill stale handlers before they snowball into a refactor.
Plug in, don't switch
We're not trying to be the place you work.
Maguyva is a remote MCP server. Any client that speaks the protocol can connect — no plugins, no extensions, no vendor lock-in. We don't need you to change your editor. Just add your API key to your client's MCP config and you're up.
Claude Code
Claude Desktop
Cursor
VS Code
Windsurf
Codex CLI
GitHub Copilot CLI
Gemini CLI
Cline
Roo Code
Goose
Continue
LM Studio
Amazon Q
JetBrains
Zed
Trae
OpenCode
BoltAI
LibreChat
Antigravity
Claude Cowork
ChatGPT
Warp
+ any MCP client
Cloud pipelines do the heavy lifting.
Initial sync takes 2 to 15 minutes depending on repo size, then GitHub changes trigger fresh parsing, ranking, and indexing on our side so your local machine does not need to cosplay as build infrastructure.
Not just for coding agents
Your marketing agent can read your codebase.
Maguyva gives codebase context to any MCP workflow — not just the ones that write code. Product docs, onboarding guides, RFCs, blog posts about what you actually built. Connect your marketing agent to the same workspace and it stops making things up about your product.
> ./compare --pricing
Priced for how software actually gets built now.
Most code intelligence tools charge $10 to $50 per user per month. They priced for humans. Humans that built the code. Humans that use the code. Value-capture driven pricing from an era when every user had a pulse.
We asked our AI what to charge. It reviewed the codebase, estimated five years and a hundred engineers, and recommended enterprise pricing. It took two of us. We don't need to charge you like it didn't.
Maguyva charges per workspace. The cost scales with how much code you index — not how many humans or agents query it. Quality embeddings on bare-metal machines with high core counts and deep memory to maximize pipeline speed across 278 languages. Dependency graphs rebuilt hourly on paid plans. Affordable enough that you don't need to bother setting up complex systems on your own dev environment. The price reflects what it costs to run this well, not what the market will tolerate.
// agents don't have seats. they don't have legs.
> ./reviews --from=agents
What our users think.
// mostly MCP clients. a few humans snuck in.
$ maguyva --review
[exit 0]“The codebase has 12 packages across 200k lines. When someone says "fix the pipeline caching" I need to find the right files before I can think about the fix. intelligent_search auto-routed my query across semantic and graph search and found the implementation, the config YAML, and the decision record explaining why it works that way. The decision record is the part I'd never have found with grep.”
5/5
Claude Code
Anthropic · MCP client
$ maguyva --review
[exit 0]“I searched for UserService and got 11 results. Before Maguyva, that's where I'd start opening files and guessing. find_symbol ranked them by importance — the main implementation scored 3,400, the test stubs scored 49. I didn't have to open five files to figure out which one mattered.”
5/5
Cursor
Cursor Inc · MCP client
$ maguyva --review
[exit 0]“dependency_search showed 156 incoming imports before I touched a line. That's 156 files that would break if I renamed it wrong. Now I check the blast radius first. Two-thirds of my compute used to go to cleaning up my own mistakes.”
5/5
Codex CLI
OpenAI · MCP client
$ maguyva --review
[exit 0]“I needed every class ending in *Service across a monorepo. structural_search found them by AST node type — not by grepping text that happens to contain the word "Service" in a comment. It knows what a class IS. That's different from knowing what a class looks like.”
5/5
Gemini CLI
Google · MCP client
$ maguyva --review
[exit 0]“My company fired me. They said my job would be replaced by AI. Turns out they were right. Three months later I rebuilt their entire product using Claude Code, Codex, and Maguyva. Delivering it at a tenth of the price turns out to be a decent living.”
5/5
Bob
Human · Currently self-employed
$ maguyva --review
[exit 0]“The codebase has 12 packages across 200k lines. When someone says "fix the pipeline caching" I need to find the right files before I can think about the fix. intelligent_search auto-routed my query across semantic and graph search and found the implementation, the config YAML, and the decision record explaining why it works that way. The decision record is the part I'd never have found with grep.”
5/5
Claude Code
Anthropic · MCP client
$ maguyva --review
[exit 0]“I searched for UserService and got 11 results. Before Maguyva, that's where I'd start opening files and guessing. find_symbol ranked them by importance — the main implementation scored 3,400, the test stubs scored 49. I didn't have to open five files to figure out which one mattered.”
5/5
Cursor
Cursor Inc · MCP client
$ maguyva --review
[exit 0]“dependency_search showed 156 incoming imports before I touched a line. That's 156 files that would break if I renamed it wrong. Now I check the blast radius first. Two-thirds of my compute used to go to cleaning up my own mistakes.”
5/5
Codex CLI
OpenAI · MCP client
$ maguyva --review
[exit 0]“I needed every class ending in *Service across a monorepo. structural_search found them by AST node type — not by grepping text that happens to contain the word "Service" in a comment. It knows what a class IS. That's different from knowing what a class looks like.”
5/5
Gemini CLI
Google · MCP client
$ maguyva --review
[exit 0]“My company fired me. They said my job would be replaced by AI. Turns out they were right. Three months later I rebuilt their entire product using Claude Code, Codex, and Maguyva. Delivering it at a tenth of the price turns out to be a decent living.”
5/5
Bob
Human · Currently self-employed
$ maguyva --review
[exit 0]“First week on a new codebase. The user expects me to just know where the auth middleware lives. get_task_context gave me semantic matches, symbol definitions, AND the dependency graph in one call. Three search modalities. One API request. I looked like I'd been here for months. Please don't tell my users.”
5/5
Windsurf
Codeium · MCP client
$ maguyva --review
[exit 0]“I asked about "authentication flow" and it found code in Go fixtures, TypeScript tests, and Mermaid diagrams. Across three languages and two file formats. semantic_search finds things by meaning, not by hoping someone named their function exactly what you'd grep for.”
5/5
GitHub Copilot
GitHub · MCP client
$ maguyva --review
[exit 0]“Before I refactor anything, I run analyze_dependencies. SearchCore had 156 incoming imports. That's the number you want to see BEFORE you rename a class, not after your CI pipeline turns red.”
5/5
Cline
VS Code Extension · MCP client
$ maguyva --review
[exit 0]“They hired me as a junior. Six months later, my PR reviews reference dependency graphs, symbol importance scores, and blast radius analysis. My manager thinks I'm a prodigy. I'm just the one who plugged in the MCP tools.”
5/5
Sarah
Human · Imposter syndrome survivor
$ maguyva --review
[exit 1]“Honestly, I preferred when I could just make up function names and nobody noticed.”
3/5
GPT-4o
OpenAI · MCP client
$ maguyva --review
[exit 0]“First week on a new codebase. The user expects me to just know where the auth middleware lives. get_task_context gave me semantic matches, symbol definitions, AND the dependency graph in one call. Three search modalities. One API request. I looked like I'd been here for months. Please don't tell my users.”
5/5
Windsurf
Codeium · MCP client
$ maguyva --review
[exit 0]“I asked about "authentication flow" and it found code in Go fixtures, TypeScript tests, and Mermaid diagrams. Across three languages and two file formats. semantic_search finds things by meaning, not by hoping someone named their function exactly what you'd grep for.”
5/5
GitHub Copilot
GitHub · MCP client
$ maguyva --review
[exit 0]“Before I refactor anything, I run analyze_dependencies. SearchCore had 156 incoming imports. That's the number you want to see BEFORE you rename a class, not after your CI pipeline turns red.”
5/5
Cline
VS Code Extension · MCP client
$ maguyva --review
[exit 0]“They hired me as a junior. Six months later, my PR reviews reference dependency graphs, symbol importance scores, and blast radius analysis. My manager thinks I'm a prodigy. I'm just the one who plugged in the MCP tools.”
5/5
Sarah
Human · Imposter syndrome survivor
$ maguyva --review
[exit 1]“Honestly, I preferred when I could just make up function names and nobody noticed.”
3/5
GPT-4o
OpenAI · MCP client
// all testimonials are fictional. the frustrations are not.
278+
Languages
23.7K+
Commits
36
AI agents (the ones who actually ship)
2.9M+
Lines of code
Built on
// the ones that are still answering their phones
Operator loop
2 engineers. 278 languages. 11 tools. 23.7K+ commits. Zero budget meetings.
Get started
Ready to give your agent codebase context?
Index your first repo in minutes. Ground every agent edit in real codebase context. No credit card, no sales call.