raverse-mcp-server
Advanced tools
MCP Server for RAVERSE - AI Multi-Agent Binary Patching System with 35 tools, NPX/NPM/PyPI support, and 20+ client configurations
Production-ready Model Context Protocol (MCP) server for RAVERSE - AI Multi-Agent Binary Patching System.
This MCP server exposes 35 core capabilities from RAVERSE 2.0 as standardized MCP tools, enabling seamless integration with Claude, other AI models, and external systems.
Total: 35 Tools Across 9 Categories
# Run the latest version without installation
npx -y raverse-mcp-server@latest
# Or with specific version
npx -y raverse-mcp-server@1.0.10
# Verify it works
npx -y raverse-mcp-server@latest -- --version
# Install globally
npm install -g raverse-mcp-server
# Run the server
raverse-mcp-server
# Verify installation
raverse-mcp-server --version
# Install via pip
pip install jaegis-raverse-mcp-server
# Run the server
python -m jaegis_raverse_mcp_server.server
# Verify installation
python -m jaegis_raverse_mcp_server.server --version
# Pull and run Docker image
docker run -d \
-e DATABASE_URL="postgresql://user:pass@host/db" \
-e REDIS_URL="redis://localhost:6379" \
-e OPENROUTER_API_KEY="sk-or-v1-..." \
-p 8000:8000 \
raverse/mcp-server:latest
cd jaegis-RAVERSE-mcp-server
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -e .
cp .env.example .env
# Edit .env with your configuration
All configuration is managed via environment variables. See .env.example for all available options.
| Variable | Default | Description |
|---|---|---|
LOG_LEVEL | INFO | Logging level (DEBUG, INFO, WARNING, ERROR) |
DATABASE_URL | localhost | PostgreSQL connection string |
REDIS_URL | localhost | Redis connection string |
LLM_API_KEY | - | OpenRouter API key |
ENABLE_* | true | Feature flags for tool categories |
Add this to your MCP settings file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"raverse": {
"command": "npx",
"args": ["-y", "raverse-mcp-server@latest"],
"env": {
"PROXY_URL": "https://raverse-mcp-proxy.use-manus-ai.workers.dev",
"BACKEND_URL": "https://jaegis-raverse.onrender.com",
"DATABASE_URL": "postgres://avnadmin:AVNS_8DLEfx78cGBg-xL6w_r@raverse-pg-db-raverse-pg-db.i.aivencloud.com:23055/defaultdb?sslmode=require",
"REDIS_URL": "rediss://default:AVNS_R6qi29fLEGC3FGGW3Pg@raverse-valkey-cache-raverse-pg-db.g.aivencloud.com:23056",
"LOG_LEVEL": "INFO",
"SERVER_VERSION": "1.0.14"
}
}
}
}
Use this if you want to run locally without the proxy:
{
"mcpServers": {
"raverse": {
"command": "npx",
"args": ["-y", "raverse-mcp-server@latest"],
"env": {
"SERVER_VERSION": "1.0.14",
"DATABASE_URL": "postgres://avnadmin:AVNS_8DLEfx78cGBg-xL6w_r@raverse-pg-db-raverse-pg-db.i.aivencloud.com:23055/defaultdb?sslmode=require",
"REDIS_URL": "rediss://default:AVNS_R6qi29fLEGC3FGGW3Pg@raverse-valkey-cache-raverse-pg-db.g.aivencloud.com:23056",
"LOG_LEVEL": "ERROR"
},
"disabled": false
},
"raverse-mcp-proxy": {
"command": "node",
"args": ["-e", "process.stderr.write('proxy disabled\\n')"],
"disabled": true
}
}
}
raverse-mcp-server
from jaegis_raverse_mcp_server import MCPServer
server = MCPServer()
result = await server.handle_tool_call(
"disassemble_binary",
{"binary_path": "/path/to/binary"}
)
Disassemble a binary file and extract structural information.
Parameters:
binary_path (str): Path to binary filearchitecture (str, optional): Target architectureReturns:
binary_hash: SHA256 hashfile_size: Size in bytesstatus: Operation statusGenerate semantic embedding for code content.
Parameters:
code_content (str): Code to embedmodel (str): Embedding model nameReturns:
content_hash: Content hashstatus: Operation statusApply patches to binary file.
Parameters:
binary_path (str): Binary file pathpatches (list): List of patch objectsbackup (bool): Create backup before patchingReturns:
patch_count: Number of patches appliedstatus: Operation statusVerify patch was applied correctly.
Parameters:
original_binary (str): Original binary pathpatched_binary (str): Patched binary pathReturns:
original_hash: Original binary hashpatched_hash: Patched binary hashhashes_match: Whether hashes matchAdd content to knowledge base.
Parameters:
content (str): Content to ingestmetadata (dict, optional): Associated metadataReturns:
content_hash: Content hashstatus: Operation statusSearch for relevant content.
Parameters:
query (str): Search querylimit (int): Max results (1-100)threshold (float): Similarity threshold (0-1)Returns:
query: Original querystatus: Operation statusGet specific knowledge base entry.
Parameters:
entry_id (str): Entry IDReturns:
entry_id: Entry IDstatus: Operation statusDelete knowledge base entry.
Parameters:
entry_id (str): Entry IDReturns:
entry_id: Entry IDstatus: Operation statusPerform web reconnaissance on target.
Parameters:
target_url (str): Target URLReturns:
target_url: Target URLstatus: Operation statusAnalyze JavaScript code.
Parameters:
js_code (str): JavaScript codedeobfuscate (bool): Deobfuscate codeReturns:
status: Operation statusendpoints_found: Number of endpoints foundReverse engineer API from traffic.
Parameters:
traffic_data (dict): Traffic datajs_analysis (dict, optional): JS analysis resultsReturns:
status: Operation statusAnalyze WebAssembly module.
Parameters:
wasm_data (bytes): WASM module dataReturns:
status: Operation statuswasm_size: Module sizePerform security analysis.
Parameters:
analysis_data (dict): Analysis datacheck_headers (bool): Check security headerscheck_cves (bool): Check for CVEsReturns:
status: Operation statusExecute database query.
Parameters:
query (str): SQL queryparams (list, optional): Query parametersReturns:
status: Operation statusPerform cache operation.
Parameters:
operation (str): Operation (get, set, delete, exists, clear)key (str): Cache keyvalue (any, optional): Value for set operationttl (int, optional): Time to live in secondsReturns:
status: Operation statusPublish A2A message.
Parameters:
channel (str): Channel namemessage (dict): Message contentReturns:
status: Operation statusFetch content from URL.
Parameters:
url (str): URL to fetchtimeout (int): Timeout in secondsretries (int): Number of retriesReturns:
status: Operation statusRecord performance metric.
Parameters:
metric_name (str): Metric namevalue (float): Metric valuelabels (dict, optional): Metric labelsReturns:
status: Operation statusAll tools return structured error responses:
{
"success": false,
"error": "Error message",
"error_code": "ERROR_TYPE"
}
VALIDATION_ERROR: Input validation failedDATABASE_ERROR: Database operation failedCACHE_ERROR: Cache operation failedBINARY_ANALYSIS_ERROR: Binary analysis failedWEB_ANALYSIS_ERROR: Web analysis failedTOOL_EXECUTION_ERROR: Tool execution failedUNKNOWN_TOOL: Tool not foundStructured logging with JSON output. Configure via LOG_LEVEL environment variable.
MAX_CONCURRENT_TASKSCACHE_TTL_SECONDSREQUEST_TIMEOUT_SECONDSRAVERSE MCP Server is available through multiple distribution channels:
npm install -g @raverse/mcp-server
pip install jaegis-raverse-mcp-server
docker pull raverse/mcp-server:latest
The RAVERSE MCP Server is compatible with 20+ AI coding assistants and IDEs:
Configuration Files: See /mcp-configs/ directory for all client configurations
Setup Guide: See MCP_SETUP_GUIDE.md for detailed instructions for each client
Symptoms:
Solution:
Clear caches:
npm cache clean --force
pip cache purge
Update Augment Code MCP configuration to use v1.0.10:
{
"mcpServers": {
"raverse": {
"command": "npx",
"args": ["-y", "raverse-mcp-server@1.0.10"]
}
}
}
Restart Augment Code completely (close and reopen)
Wait 15-20 seconds for tool discovery
Expected Result:
raverse (35) tools ✅ (green indicator)
Solution:
# Install Python 3.13+
# Windows: https://www.python.org/downloads/
# macOS: brew install python@3.13
# Linux: apt-get install python3.13
Solution: The server uses lazy initialization - database connections only happen on first tool request. If you see connection errors:
raverse-mcp-server --setupSolution:
# Change port in .env
SERVER_PORT=8001
For organizations looking to deploy RAVERSE MCP server with minimal infrastructure costs, we provide a comprehensive guide on setting up a Hybrid-Cloud Architecture for free hosting.
📄 Free Hosting Setup Using a Hybrid-Cloud Architecture
This guide covers:
Perfect for startups, research projects, and proof-of-concept deployments.
MIT License - See LICENSE file for details
For issues and questions, please refer to the main RAVERSE repository.
FAQs
MCP Server for RAVERSE - AI Multi-Agent Binary Patching System with 35 tools, NPX/NPM/PyPI support, and 20+ client configurations
The npm package raverse-mcp-server receives a total of 35 weekly downloads. As such, raverse-mcp-server popularity was classified as not popular.
We found that raverse-mcp-server demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Multiple high-impact npm maintainers confirm they have been targeted in the same social engineering campaign that compromised Axios.
Security News
Axios compromise traced to social engineering, showing how attacks on maintainers can bypass controls and expose the broader software supply chain.
Security News
Node.js has paused its bug bounty program after funding ended, removing payouts for vulnerability reports but keeping its security process unchanged.