Skip to main content
Glama
ourobx

agent-ebpf-mcp

by ourobx

๐Ÿ›ก๏ธโšก Agent-eBPF: AI Sentinel in Kernel Space

Agent-eBPF is a sub-microsecond (<35ยตs) Linux kernel space (Ring 0) security shield and telemetry gateway engineered for autonomous AI agents, LLM services, and containerized application swarms.

Operating under Zero-Trust principles, this architecture intercepts destructive database queries, illegal network packets, and unauthorized system calls (such as unconstrained DELETE/UPDATE operations without WHERE clauses) directly inside the Linux kernel (XDP/Ring-Buffer) with zero latency impact.

๐Ÿš€ Quick Start (1-Click Launch)

Launch the Agent-eBPF system and Visual Web Dashboard instantly without manual setup or configuration:

๐Ÿ’ป Windows

Double-click the launcher script in the project root:

start.bat

๐Ÿง Linux / ๐ŸŽ macOS

Run the shell script in terminal or file manager:

chmod +x start.sh
./start.sh

๐Ÿ’ก Automatic Execution: The launcher validates dependencies, installs necessary Python packages, initializes the eBPF & MCP Gateway server, and automatically opens http://localhost:8000 in your default web browser.


Related MCP server: Phantom MCP

๐Ÿ–ฅ๏ธ Visual Web Control Panel (Web UI)

Manage kernel security operations visually without writing code via the Web UI (http://localhost:8000):

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚ ๐Ÿ›ก๏ธโšก Agent-eBPF | Autonomous Linux Kernel Shield                       โ”‚
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚                                                                        โ”‚
โ”‚  [1. LIVE TELEMETRY]          [2. AST SANDBOX]                         โ”‚
โ”‚  โ€ข Real-time Kernel Logs      โ€ข Test sample SQL query:                 โ”‚
โ”‚  โ€ข Dropped Packet Stream      โ€ข UPDATE users SET role='admin'          โ”‚
โ”‚  โ€ข Latency (<35ยตs)            โ€ข [โšก EVALUATE] -> Blocked (DROP)        โ”‚
โ”‚                                                                        โ”‚
โ”‚  [3. RULE POLICIES]           [4. MCP SSE CONNECTION]                  โ”‚
โ”‚  โ€ข policy.yaml Preview        โ€ข SSE Endpoint Address:                  โ”‚
โ”‚  โ€ข 1-Click Policy Injection   โ€ข http://localhost:8000/sse              โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
  1. Interactive AST Sandbox: Test destructive DELETE or UPDATE queries live and observe kernel-level sub-microsecond interception in real time.

  2. Live Telemetry Stream: Monitor database mutations and system calls issued by AI agents through a streaming event terminal.

  3. Policy & Rule Management: View active security policies (policy.yaml) and dynamically inject enforcement rules.


๐Ÿค– AI Agent Integration (MCP SSE)

Agent-eBPF provides native support for Model Context Protocol (MCP) via Server-Sent Events (SSE).

MCP Server Connection

  • SSE Endpoint: http://localhost:8000/sse

  • Messages Endpoint: http://localhost:8000/messages

  • OAuth 2.0 Discovery: http://localhost:8000/.well-known/oauth-authorization-server

Exposed MCP Tools

  • get_security_status: Fetches active kernel hooks, inspection latency, and blocked threat metrics.

  • get_ebpf_status: Retrieves real-time BPF map packet counters and kernel hook state.

  • get_active_policies: Fetches declarative rules loaded from policy.yaml.

  • add_security_rule: Injects new IP block entries or query enforcement rules into kernel memory.

  • simulate_query_check: Validates proposed SQL payloads against active eBPF policies prior to execution.


๐Ÿ’ป CLI Command Line Interface

Manage Agent-eBPF via the rich command-line tool cli.py:

# Build eBPF C bytecode
python cli.py build

# Load eBPF program into kernel (eth0)
python cli.py load --iface eth0

# Inspect kernel status and packet counters
python cli.py status

# Stream live RingBuffer security violations
python cli.py events

# Add IP block rule to BPF map
python cli.py add-rule 192.168.1.105 --rule-id 201

# Unload eBPF program from kernel
python cli.py unload --iface eth0

๐Ÿ“š Developer Guide & Technical Specs

For in-depth kernel architecture details, zero-overhead execution specs, declarative rule schemas, and production deployment patterns, refer to the Developer Guide.


๐Ÿ”ฌ Automated Testing

Run the full pytest suite to verify MCP endpoints, JWT authentication, and eBPF loader contracts:

python -m pytest -v

๐Ÿ“œ License

Distributed under the MIT License. Created by Sysauto & Agent-eBPF Core Engineering.

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
โ€“Release cycle
โ€“Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    D
    maintenance
    An AI-Native OS Core that enables LLMs to autonomously monitor, control, and optimize Linux systems with 200+ system control tools covering process management, security, containers, and self-editing capabilities.
  • F
    license
    -
    quality
    D
    maintenance
    Enables authorized compliance verification and security auditing through natural language, bridging AI assistants with industry-standard security tools for enterprise audits.
    24
  • F
    license
    -
    quality
    B
    maintenance
    Enables LLMs to safely write and run bpftrace scripts against the Linux kernel for observability, with explicit probe allowlists and execution timeout.
    1

View all related MCP servers

Related MCP Connectors

  • Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.

  • Runtime permission, approval, and audit layer for AI agent tool execution.

  • See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ourobx/agent-ebpf'

If you have feedback or need assistance with the MCP directory API, please join our Discord server