Looking for the full autonomous platform? Check out Myelix Agents .

Stop paying your AI agent to blindly grep whitespace.

Standard coding agents waste 70% of context tokens re-reading raw files with shell grep. Synapse-MCP indexes your codebase into a sub-millisecond local AST graph—giving Claude Code, Cursor, and Windsurf exact caller trees, 60% lower token spend, and zero-hallucination refactoring.

Compatible with all major IDEs and agents via the open Model Context Protocol (MCP).

CursorClaude CodeWindsurfGitHub CopilotDevinAiderClineVS CodeJetBrains AICursorClaude CodeWindsurfGitHub CopilotDevinAiderClineVS CodeJetBrains AI

50 Languages. One Graph.

Synapse indexes, chunks, and extracts dependency edges for every mainstream programming language out of the box — no plugins, no configuration, no cloud.

Functional Systems / Low-level OO / General-purpose Educational / Scripting / IoT Data / Markup
Elixir Erlang Haskell F# OCaml Clojure Scala Python JavaScript TypeScript Go Ruby Rust Java C / C++ C# Kotlin Swift PHP Dart Perl R Zig Objective-C Groovy Julia SQL HTML CSS JSON Markdown YAML XML TOML HCL Dockerfile Protocol Buffers GraphQL Solidity PowerShell Pascal Lisp VBA Smalltalk Prolog Lua Assembly Shell Tcl Arduino

Why standard context engines fail your agents

Whether you use a free open-source script or an expensive enterprise cloud engine, your agents are still flying blind. Here is what actually happens under the hood when your AI tries to understand your code.

01 FAILURE

The Open-Source Trap: "The Context Bloater"

Free MCP tools and WASM indexers simply automate terminal commands or dump graph database queries directly into the LLM. If your agent asks to see a 10-line function, the tool dumps the entire 3,000-line file into your prompt. You exhaust your context window, confuse the AI with irrelevant background noise, and pay astronomical API bills just to read bracket syntax.

02 FAILURE

The Enterprise Cloud Trap: "The IP Leak"

Expensive enterprise context engines upload your proprietary codebase to their cloud to perform fuzzy semantic searches. They match strings, but they lack active write-validation. You trigger massive InfoSec and compliance headaches. Worse, because they don't simulate edits locally, they happily allow the AI to write code that breaks your downstream architecture.

03 ADVANTAGE

The Synapse Advantage: AST-Aware Local Intelligence

Synapse-MCP is a compiled, zero-dependency binary that runs 100% locally. It builds a mathematical Abstract Syntax Tree (AST) graph of your code. When an agent asks for context, Synapse strips out the noise and returns only compressed structural signatures. Before an agent writes a file, Synapse simulates the edit to mathematically prove it will not break the build.

The Proof: Autonomous Security Audit on a 500k LOC Monorepo

Same frontier model. Same task. Same vulnerabilities found. The only difference was the context engine.

We tasked an AI agent with auditing a production codebase. The baseline agent used standard shell and grep tools. The second agent used Synapse-MCP exclusively.

−60% Cost & Tokens
2.2× Faster
100% Accuracy

Elixir codebase · same frontier model · autonomous security audit

Standard Agent (Shell/Grep) Synapse-MCP Agent
Total Tokens
Shell
6,218,045
Synapse
2,487,914
-60%
API Cost
Shell
$12.63
Synapse
$5.05
-60%
Wall-Clock
Shell
16m 56s
Synapse
7m 36s
2.2× faster
Agent Actions
Shell
68 bash calls
Synapse
36 MCP calls
-47%
Vulns Found
Shell
3 Critical
Synapse
3 Critical
identical

Deploy Synapse-MCP

A fully compliant MCP server. Plug it into any compatible client in 60 seconds and get persistent structural code intelligence everywhere your team works.

​■ 100% Local 🔒 End-to-End Encrypted ⚡ Sub-second Queries
Free

Free — The "Golden Graph"

  • Instant Local Indexing: Maps 10,000+ files across 50 languages in seconds with zero cloud dependencies.
  • AST-Aware Minification: Stops context exhaustion by shrinking file payloads before sending them to the LLM.
  • Three Search Modes: Ask in plain English, look up by symbol, or search by regex pattern.
  • Codebase Insights: Automatically detects language breakdowns, public API surfaces, and refactor opportunities.
  • Zero-Config Setup: Add 5 lines to your cursor_settings.json and start immediately.
Most Popular

Pro — The "Shadow Graph" ($19/month)

  • Simulated Safe Writes: Edits are verified in memory before touching disk. Rolls back automatically if an edit breaks a caller's signature.
  • Impact & Caller Analysis: Shows every caller and dependency affected across your entire repository in under 500ms.
  • Instant Crash Resolution: Maps stack traces directly to your AST graph for instant root-cause analysis.
  • Test Intelligence: Surfaces exact coverage gaps and recommends precise test targets without running a test suite.
  • Persistent Agent Memory: Insights and summaries learned by the AI are saved to the graph, making your codebase smarter across sessions.

13 Precision Tools. One Context Engine.

Cut Your Token Bills by 60%

If your agent asks how a PaymentService works, standard tools send a 3,000-line JSON payload. Synapse parses the AST, strips out the internal function bodies, and sends a surgically compressed 150-token outline containing only public interfaces and outbound edges. Your agent gets 10× the repository structure for a fraction of the cost.

Traditional agents: Dump the entire file. Pay for every token of whitespace and boilerplate.

Understand How Your Changes Ripple

Ask your agent, "What happens if I change this User struct?" Standard agents will grep and guess. Synapse maps the exact impact — every inbound caller, downstream callee, and interface contract across your entire codebase. You see what will break before the AI writes a single line.

Traditional agents: Write first, discover breakage second.

Edits That Are Proven Before They Save

When standard agents write code, you just have to cross your fingers and hope it compiles. When a Synapse-powered agent writes code, Synapse creates a simulated Shadow Graph in memory. If the AI's edit breaks a function signature on the other side of your project, Synapse rejects the edit before it is ever written to disk.

Traditional agents: Write raw to disk and leave broken code for you to debug.

Instant Crash Resolution

Paste a stack trace to your AI. Standard agents do a slow, inaccurate text search. Synapse parses the runtime crash, matches the exact frames to indexed chunks in your local codebase, and traces the execution path to pinpoint the root cause — without you ever needing to boot up the application.

Traditional agents: String search the trace, open files manually, guess at root cause.

Write Tests That Actually Matter

Tell your agent to "write tests for this module." Standard tools run the whole test suite and guess at the inputs. Synapse highlights exactly which lines of code are currently unprotected. The AI writes behavioural tests that patch real, structural gaps.

Traditional agents: Run the full test suite and guess what is covered.

100% Local. Zero IP Leakage.

Enterprise CISOs do not want proprietary code uploaded to third-party databases. Synapse is a compiled, highly optimised binary that runs entirely on your local machine. Your codebase never leaves your laptop. No cloud. No compliance headaches.

Traditional agents: Upload your codebase to third-party cloud search engines.

How engineering teams actually use Synapse

Standard AI chat windows are great for writing boilerplate, but they struggle with complex, multi-file software engineering. Here is how adding Synapse changes the workflow for real engineering tasks.

01

Complex Architectural Refactoring

The Scenario: You ask your AI to decouple a legacy Auth module.

❌ Standard AI

Runs a blind text search for "auth", updates the files it finds, misses a dozen references in nested background workers, and leaves your project with broken imports that you have to manually hunt down.

✅ Synapse-MCP

Your agent queries the graph in under 500ms to map every caller across your 4 sub-services. It systematically rewrites the callers and verifies the new function signatures against the AST in memory—delivering a structurally safe refactor without broken runtime imports.

02

Deep-Dive Bug Hunting

The Scenario: A production webhook drops a payload and returns a 500 error.

❌ Standard AI

Asks you to manually find and paste in five different files so it can try to guess how they connect, losing context along the way.

✅ Synapse-MCP

You paste the raw stack trace into your chat. Synapse parses the frames and maps them directly to your indexed local graph. Instead of guessing, the agent traces the execution path backwards, surfacing the likely root cause and saving you an hour of manual file-hopping.

03

Semantic Code Reviews

The Scenario: A junior developer opens a dense, 500-line Pull Request.

❌ Standard AI

Reads the flat text diff and flags a missing type hint or a poorly named variable. It has no idea how the changed files affect the rest of the application.

✅ Synapse-MCP

The agent overlays the PR diff onto your codebase's AST graph. Because it understands the wider architecture, it can flag actual downstream regressions: "This PR looks fine syntactically, but it removes an event emission that EmailService relies on." You get a structural impact review, rather than just a shallow syntax checker.

04

Precision Testing & Coverage

The Scenario: You inherit an older module with 30% test coverage and ask the AI to improve it.

❌ Standard AI

Generates useless "happy path" boilerplate tests that heavily mock dependencies and catch zero real bugs, just to inflate the coverage metric.

✅ Synapse-MCP

The agent traverses the local graph to pinpoint the exact logical branches that lack coverage. Instead of guessing at the inputs, it sees exactly which edge cases are exposed ("The failure state in validate_checkout() is completely untested") and writes targeted, behavioural tests that actually verify the system.

Frequently Asked Questions

Everything you need to know about Synapse MCP, setup instructions, and optimizing AI coding agents.

What is Synapse MCP and how does it work?
Synapse MCP is a persistent, local code-knowledge graph server operating over the Model Context Protocol (MCP). Instead of forcing your AI agent to rely on string-matching grep or uncompressed file reads, Synapse indexes your entire codebase into AST chunks, call edges, and semantic embeddings. It provides 100% accurate caller/callee graphs and compressed code contexts in a single tool call.
How fast are Synapse MCP graph queries?
Synapse graph lookups execute in microseconds to nanoseconds locally in-memory. Indexing a 10,000-file repository takes only seconds, and Virtual Worktree Overlays (VWO) apply sub-50ms delta indexes when running parallel sub-agents in Git worktrees.
What is the difference between the Free and Pro editions?
  • Free Edition ("Golden Graph" — $0): Full AST indexing, 3 search modes (symbol, regex, semantic), context retrieval (find, explain, onboard), file inspection, standard writes, and unlimited repositories.
  • Pro Edition ("Shadow Graph" — $19/mo): Everything in Free, plus deep graph exploration (callers/callees/cycles), pre-edit safety packs, simulated safe writes with linter validation (write_safely with dry-run), crash stack trace resolution (resolve_stack), test quality analysis (find_tests), persistent encrypted knowledge cache, and unlimited repositories.
How does Synapse Pro pay for itself?
Frontier model API costs range from $3 to $15 per 1M tokens. By cutting prompt token consumption by 30-60% via SmartCrusher minification and replacing 5-10 grep+read turns with single-turn microsecond graph lookups, Synapse saves approximately $0.25 to $0.50 per session in raw API spend, paying for its $19/mo subscription within 48 hours of active development.
How does Synapse differ from simple Vector RAG or RepoMix text dumps?
Vector RAG engines slice files by line count, chopping functions in half and missing imported function aliases. RepoMix dumps uncompressed 30,000-line text files into the prompt, destroying your context window. Synapse parses exact compiler AST nodes, builds transitive caller trees, and compresses payloads by 30-60% before sending them to the LLM.
What capabilities does Synapse MCP provide to my AI agent?
Synapse exposes 13 consolidated MCP tools covering:
  • Exploration & Search: Semantic search, symbol lookups, regex searches, and single-turn transitive caller/callee graph traversal.
  • Context Curation: Pre-edit safety packs, code chunk explanations, onboarding order, and outline signature scanning.
  • Safe Modifications: In-memory simulated file writes with automatic lint validation and dry-run pre-checks.
  • Impact & Diagnostics: Sub-500ms caller/callee impact mapping (showing your agent every caller affected across the codebase before edits touch disk), crash stack trace resolution to AST chunks, test coverage mapping, and cycle detection.
How do I install and configure Synapse MCP?
Install the launcher via npx @myelixlabs/synapse-mcp install. This auto-configures your IDE or agent (Claude Code, Cursor, Antigravity, Windsurf, Cline, Zed, VS Code).
How do I activate Pro after upgrading?

After checkout succeeds, refresh the entitlement cached by your local installation to unlock Pro immediately. Choose any of these:

  1. Press Open Synapse (opens synapse://billing/complete in the Synapse app).
  2. OR Open the local Synapse Dashboard and press Refresh in the User tab.
  3. OR Run npx @myelixlabs/synapse-mcp auth refresh in your terminal.
Why is configuring AGENTS.md or SKILL.md rules mandatory?

Frontier LLMs (Claude Sonnet 5, GPT-5.6 Sol, Gemini 3.6 Flash, Grok 4.5) are heavily pre-trained on Unix command examples, creating strong default "muscle memory" toward grep and raw file reads. Without an explicit rule in your agent's system prompt (e.g. .agents/skills/synapse-mcp/SKILL.md or AGENTS.md), the agent will default to standard shell commands and ignore the MCP server.

Running npx @myelixlabs/synapse-mcp install automatically registers the MCP-First Discovery Policy across detected agent configuration paths (~/.gemini/config/AGENTS.md, ~/.claude/CLAUDE.md, .cursorrules, etc.) to enforce tool usage.

Does Synapse MCP send my codebase to the cloud?
No. Synapse MCP runs entirely on your local machine as a stdio/HTTP process. All AST indexing, graph storage, SQLite persistence, and embedding computations happen locally. Your source code is not uploaded to Myelix Labs as part of normal local indexing or search. A free Synapse account (email or Sign in with Google) is required for dashboard access, licensing, and device activation — that account is separate from local indexing and does not receive your source code.
Why do I need an account, and why Sign in with Google?

A free Synapse account is required to use Synapse MCP. The account powers the web dashboard, licensing, and device activation so you can authorize the local MCP client on your machine. You can create that account with email and password or with Sign in with Google.

Sign in with Google is one of the ways to create or access your account. Synapse requests your Google email address and basic identity solely to create or sign you into your Synapse account, confirm your email, and link device approvals and subscriptions to the right user. We do not request access to Gmail, Drive, Contacts, or other Google services, and we do not use Google sign-in to read or upload your codebase.

Details are in our Privacy Policy.

Is Synapse MCP compatible with multi-app umbrella repositories and Git worktrees?
Yes. Synapse transparently detects Git worktrees and applies Virtual Worktree Overlays (VWO) with near-instant delta indexing (<50ms), allowing multiple sub-agents to operate in parallel worktrees without duplicating graph indexes.

Latest Engineering Insights

Deep dives into LLM context optimization, graph-based code retrieval, and agentic workflows.

Architecture

Why Synapse MCP Beats Native IDE Indexers (Cursor, Windsurf, Warp)

An architectural deep dive into why Synapse MCP's local AST graph and zero-latency file events beat cloud-based RAG and Merkle trees used by Cursor and Windsurf.

Read Article →
Benchmarks

2ms vs. 12 Seconds: Benchmark Proves Why AI Agents Need AST Graphs, Not Grep Chains

An empirical 'Show, Don't Tell' benchmark comparing traditional shell grep loops against Synapse MCP's local in-memory AST graph engine. 2ms latency vs 12s, 56.4% token savings, 85% fewer tool calls.

Read Article →
Industry Insights

The 2026 AI Developer Tooling Landscape: Why Synapse Pro is $19/mo

Full analysis across Cursor, Windsurf, Devin, Warp Terminal, Claude Pro, and Synapse. Why $20/mo is the universal price anchor and how Synapse pays for itself.

Read Article →
Technical R&D

Why LLMs Code Better with Knowledge Graphs — AST vs. Grep for Frontier AI Agents

Real data from our R&D: How replacing blind grep/read loops with AST-backed caller/callee graphs saves 30-60% of context tokens, eliminates false confidence, and solves multi-app refactoring.

Read Article →
Best Practices

Stop Letting AI Hallucinate Refactors — How Synapse Eliminates Repetitive Discovery

Why standard AI agents waste 70% of session time re-reading files, and how local AST caller graphs eliminate discovery loops for zero-breakage refactoring.

Read Article →
Architecture & Engineering

How Local Code Knowledge Graphs Work — Inside the Microsecond BEAM Engine

An architectural deep dive into in-memory graph tables, AST parsing, SmartCrusher compression, and sub-50ms Git worktree overlays.

Read Article →
View All Articles →