symapse
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@symapseexplain the architecture of this project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Symapse
Architectural awareness engine for AI coding agents
Install
npm install -g symapseRequires Node.js 22+. No dependencies. Zero config.
Related MCP server: codebase-rag
Quick Start
# Index your project
symapse index /path/to/repo
# Start the MCP server (for OpenCode/Cursor/Claude integration)
symapse mcp /path/to/repo
# Query from the terminal
symapse_ask "add notification system"
symapse_find login
symapse_map "direct login after payment"
symapse_audit 10
symapse_health
# Live coding awareness — start watching for collisions, breaks, and dead code
symapse_health --watchOpenCode Integration
Install Symapse first:
npm install -g symapseAdd to your project's opencode.json:
{
"mcp": {
"symapse": {
"type": "local",
"command": ["npx", "symapse", "mcp", "."],
"enabled": true
}
}
}Create an AGENTS.md in your project root with:
## RULE 1: Always check Symapse first
| Instead of... | Use... |
|---|---|
| Reading files for architecture | `symapse_map` |
| Grepping for symbols | `symapse_find` |
| Guessing where code goes | `symapse_ask` |
| Finding dead code or duplicates | `symapse_audit` |
| Re-indexing or checking status | `symapse_health` |
First action every session: `symapse_ask "<request>"`. If it returns questions, ASK them.
If Symapse doesn't answer your question, read files.Tools
Tool | Question it answers |
| What should I know before working on X? |
| Where is X and what does it touch? |
| Show me the shape of this repo / feature |
| What's wrong, unused, or duplicated? |
| After changes: what did I affect? What did watch detect? |
| What's the state of the index? Watch mode |
Temporal workflow:
Before coding:
symapse_ask→symapse_map→symapse_findDuring coding:
symapse_health --watchAfter each edit:
symapse_diffMaintenance:
symapse_audit|symapse_health
Supported Languages
JavaScript, TypeScript, Python, Go, Rust, C#, PHP, Ruby, Lua, and C.
How It Works
Index — walks the repo, extracts functions/classes/methods with regex parsers, builds call and import edges
Store — normalized SQLite schema, incremental by mtime + engine version
Expose — CLI, REST API, and MCP over stdio. All share the same engine.
Self-Improving
Symapse learns from agent behavior across sessions without any user involvement:
Session coherence — biases context toward the subsystem the agent is already exploring
Usage signals — logs which symbols agents actually drill into
Workflow memory — auto-detects repeated symbol sequences across sessions
Intent classification — routes config/docs questions away from source code exploration
Architecture
packages/
engine/ — regex-based parser, call graph, all analysis tools
db/ — SQLite persistence with incremental indexing
mcp/ — MCP protocol server (JSON-RPC over stdio)
apps/
cli/ — command-line entry point
api/ — HTTP API server + web dashboard
web/ — terminal-style web UILicense
AGPL-3.0
This server cannot be deployed
Maintenance
Related MCP Connectors
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Related MCP Servers
FlicenseNot gradedqualityCmaintenanceProvides AI coding agents with structured access to indexed codebases via semantic search, symbol analysis, and file reading tools.12-- AlicenseNot gradedqualityBmaintenanceEnables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, and change-impact analysis.3MIT
- FlicenseNot gradedqualityAmaintenanceProvides efficient code navigation and graph-based analysis for AI agents, enabling symbol resolution, callers, implementations, and type schemas with minimal token usage.-
- FlicenseAqualityCmaintenanceProvides codebase indexing and retrieval tools that give AI agents token-efficient, query-relevant context packages (symbols, imports, and dependencies) instead of scanning entire repositories.6-