TinyBrain 🧠
Security-Focused LLM Memory Storage with Intelligence Gathering, Reverse Engineering, and MITRE ATT&CK Integration
Tinybrain
rainmana4 ดาว
LLM local persistent storage for security nerds
- ทรานสปอร์ต
- stdio
- สถานะ
- โลคัล
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดTinyBrain is a comprehensive memory storage system designed specifically for security professionals, penetration testers, and AI assistants working on offensive security tasks. It provides intelligent memory management, pattern recognition, and comprehensive intelligence gathering capabilities through the Model Context Protocol (MCP).
serve mode)go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latestTinyBrain provides a comprehensive set of more than 50 MCP tools for complete LLM memory management:
store_memory - Store new memory entriesget_memory - Retrieve memory by IDsearch_memories - Advanced search with multiple strategiesupdate_memory - Update existing memory entriesdelete_memory - Delete memory entriesfind_similar_memories - Find similar memories by contentcheck_duplicates - Check for duplicate memoriesget_memory_stats - Get comprehensive memory statisticscreate_session - Create new security assessment sessionsget_session - Retrieve session informationlist_sessions - List all sessions with filteringcreate_task_progress - Create task progress entriesupdate_task_progress - Update task progresslist_task_progress - List task progress entriescreate_relationship - Create memory relationshipsget_related_memories - Get related memoriescreate_context_snapshot - Create context snapshotsget_context_snapshot - Retrieve context snapshotslist_context_snapshots - List context snapshotsget_context_summary - Get memory summaries for contextexport_session_data - Export session dataimport_session_data - Import session dataget_security_templates - Get predefined security templatescreate_memory_from_template - Create memories from templatesbatch_create_memories - Bulk create memory entriesbatch_update_memories - Bulk update memory entriesbatch_delete_memories - Bulk delete memory entriesget_detailed_memory_info - Get detailed memory debugging infocleanup_old_memories - Age-based memory cleanupcleanup_low_priority_memories - Priority-based cleanupcleanup_unused_memories - Access-based cleanupget_system_diagnostics - Comprehensive system diagnosticssemantic_search - AI-powered semantic searchgenerate_embedding - Generate embeddings for textcalculate_similarity - Calculate embedding similarityget_notifications - Get notifications and alertsmark_notification_read - Mark notifications as readcheck_high_priority_memories - Check for high-priority alertscheck_duplicate_memories - Check for duplicate alertshealth_check - Perform system health checksTinyBrain's security patterns and vulnerability datasets are aligned with industry-standard security frameworks:
Our security patterns and vulnerability datasets are based on authoritative sources:
Our security patterns cover 10 major programming languages with language-specific vulnerability patterns:
Download the latest release for your platform from Releases:
tinybrain_*_Darwin_arm64.tar.gztinybrain_*_Darwin_x86_64.tar.gztinybrain_*_Linux_x86_64.tar.gztinybrain_*_Linux_arm64.tar.gztinybrain_*_Windows_x86_64.zipExtract and run:
# Extract (Linux/macOS)
tar -xzf tinybrain_*_*.tar.gz
cd tinybrain_*
# Make executable
chmod +x tinybrain
# Run
./tinybrain serve
# Install latest version
go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
# Install specific version
go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
# The binary will be installed as 'tinybrain' in your $GOPATH/bin or $GOBIN
# Make sure $GOPATH/bin or $GOBIN is in your PATH
git clone https://github.com/rainmana/tinybrain.git
cd tinybrain
go build -o tinybrain ./cmd/tinybrain
docker pull rainmana/tinybrain:latest
docker run -p 8090:8090 rainmana/tinybrain
TinyBrain ships as a Claude Code plugin that registers the MCP server and installs
skills teaching Claude how to use it well (capture findings as you go, build an engagement
knowledge graph, recall it across sessions). The plugin includes a core using-tinybrain
skill plus domain workflows for code review, CTFs, and threat intelligence.
First install the binary (the plugin's MCP config runs tinybrain from your PATH):
go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
Then add the marketplace and install the plugin from inside Claude Code:
/plugin marketplace add rainmana/tinybrain
/plugin install tinybrain@tinybrain-marketplace
That's it — the tinybrain MCP server is registered (pointed at ~/.tinybrain/memory.db)
and the skills activate automatically when you do security work. To point at a different
database, set TINYBRAIN_DB_PATH in your environment before launching Claude Code.
# Start the server (data stored in ~/.tinybrain by default)
tinybrain serve
# Or specify a custom data directory
tinybrain serve --dir /path/to/your/data
# Customize the HTTP host/port (default is 127.0.0.1:8090)
tinybrain serve --port 9000
tinybrain serve --host 0.0.0.0 --port 8090
# Or use environment variables
TINYBRAIN_HOST=0.0.0.0 TINYBRAIN_PORT=9000 tinybrain serve
# Access the dashboard
open http://127.0.0.1:8090/_/
# The REST API is available at:
# http://127.0.0.1:8090/api/
In serve mode TinyBrain speaks the MCP protocol over stdio and serves the
REST API/dashboard over HTTP. Running plain tinybrain (no subcommand) starts
a stdio-only MCP server, which is what most MCP client configs use.
TINYBRAIN_API_TOKEN to require a bearer token on the REST API<dir>/memory.db (default ~/.tinybrain/memory.db)// Create an OSINT intelligence session
session := &Session{
Name: "OSINT Intelligence Gathering",
TaskType: "intelligence_analysis",
IntelligenceType: "osint",
Classification: "unclassified",
ThreatLevel: "medium",
}
// Store intelligence findings
finding := &IntelligenceFinding{
Title: "Social Media Intelligence",
IntelligenceType: "osint",
ThreatLevel: "medium",
MITRETactic: "TA0001",
MITRETechnique: "T1591",
KillChainPhase: "reconnaissance",
}
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "mcp_tinybrain-mcp-server_create_session",
"arguments": {
"name": "Security Assessment",
"task_type": "penetration_test",
"intelligence_type": "osint"
}
}
}
If you encounter issues with go install, try these solutions:
# Standard install (note the /v3 in the module path — required for v3.x)
go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
# Build from a clone instead
git clone https://github.com/rainmana/tinybrain.git
cd tinybrain
go build -o tinybrain ./cmd/tinybrain
# For Go module proxy issues, use direct mode
GOPROXY=direct go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
# For checksum database errors right after a new release
GOSUMDB=off go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest
Common Issues:
/v3 in the path — go install github.com/rainmana/tinybrain/v3/cmd/tinybrain@latest$GOPATH/bin or $GOBIN is in your PATHGOSUMDB=offAdd to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"tinybrain": {
"command": "tinybrain",
"args": ["serve"],
"env": {
"TINYBRAIN_DB_PATH": "~/.tinybrain/memory.db"
}
}
}
}
Note: The binary name is tinybrain (from cmd/tinybrain); go install github.com/rainmana/tinybrain/v3/cmd/server@latest installs the same program as server. The SQLite database is created at ~/.tinybrain/memory.db by default.
For complete documentation, API reference, and detailed guides, visit our comprehensive documentation site:
The documentation includes:
Task Types: security_review, penetration_test, exploit_dev, vulnerability_analysis, threat_modeling, incident_response, intelligence_analysis
Intelligence Types: osint, humint, sigint, geoint, masint, techint, finint, cybint
{
"name": "list_sessions",
"arguments": {
"task_type": "security_review",
"status": "active",
"limit": 10
}
}
{
"name": "store_memory",
"arguments": {
"session_id": "session_123",
"title": "SQL Injection in Login Form",
"content": "Found SQL injection vulnerability in username parameter of login form. Payload: ' OR 1=1--",
"category": "vulnerability",
"content_type": "text",
"priority": 8,
"confidence": 0.9,
"tags": "[\"sql-injection\", \"authentication\", \"critical\"]",
"source": "manual-testing"
}
}
Categories: finding, vulnerability, exploit, payload, technique, tool, reference, context, hypothesis, evidence, recommendation, note
{
"name": "search_memories",
"arguments": {
"query": "SQL injection authentication",
"session_id": "session_123",
"search_type": "semantic",
"categories": "[\"vulnerability\", \"exploit\"]",
"min_priority": 7,
"limit": 20
}
}
Search Types: semantic, exact, fuzzy, tag, category, relationship
{
"name": "get_related_memories",
"arguments": {
"memory_id": "memory_456",
"relationship_type": "exploits",
"limit": 10
}
}
{
"name": "create_relationship",
"arguments": {
"source_memory_id": "memory_123",
"target_memory_id": "memory_456",
"relationship_type": "exploits",
"strength": 0.8,
"description": "SQL injection can be used to bypass authentication"
}
}
Relationship Types: depends_on, causes, mitigates, exploits, references, contradicts, supports, related_to, parent_of, child_of
{
"name": "get_context_summary",
"arguments": {
"session_id": "session_123",
"current_task": "Analyzing authentication vulnerabilities",
"max_memories": 20
}
}
TinyBrain is built with:
/_/# Run all tests
make test
# Run tests with coverage
go test -v -race -coverprofile=coverage.out ./...
go tool cover -html=coverage.out -o coverage.html
# Run benchmarks
make bench
# Run specific test
go test -v ./internal/database -run TestNewDatabase
# Build Docker image
make docker-build
# Run container
docker run --rm -it \
-v ~/.tinybrain:/app/data \
tinybrain:latest
TINYBRAIN_DB_PATH: Path to the SQLite database (default: ~/.tinybrain/memory.db)TINYBRAIN_HOST: HTTP listen host in serve mode (default: 127.0.0.1)TINYBRAIN_PORT: HTTP listen port in serve mode (default: 8090)TINYBRAIN_HTTP: Set to false to disable the HTTP API in serve modeTINYBRAIN_API_TOKEN: If set, the REST API requires this bearer token~/.tinybrain/
├── memory.db # SQLite database
├── memory.db-wal # Write-ahead log
└── memory.db-shm # Shared memory file
The security pattern libraries, CWE references, and templates are published on the documentation site:
All security patterns are derived from authoritative sources and aligned with industry standards:
# Clone repository
git clone https://github.com/rainmana/tinybrain.git
cd tinybrain
# Setup development environment
make dev-setup
# Run tests
make test
# Build
make build
MIT License - see LICENSE file for details.
TinyBrain - Making LLM memory storage intelligent, fast, and security-focused. 🧠🔒
LLM local persistent storage for security nerds
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Tinybrain ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 LLM local persistent storage for security nerds