sandbase-harness: Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials

by sandbaseai · MCP Server · ★ 642

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install sandbase-harness

git clone https://github.com/sandbaseai/sandbase-harness.git

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 75/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agent-harnessagent-observabilityagent-pluginagent-runtimeagent-sandboxai-agentsai-infrastructureaudit-loggingdeepseek-harnessdevops

Quick Facts

Stars642
Forks78
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score75/100
Open Issues1
Last Updated2026-11-04
Created2026-07-11
Platformsdocker, k8s, mcp, node
Est. Tokens~16k

About sandbase-harness

managed-agents A local-first runtime for AI agents. Sessions, sandboxed tools, memory, credentials, audit trails, and a built-in Console — all running on your machine or in your own infrastructure. Why Agent SDKs handle the model loop.

Compatible Skills

These tools work well together with sandbase-harness for enhanced workflows:

  • dsh-cc-tui — semantic(0.46)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • cetus — semantic(0.39)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
  • dsh-TUI — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • modsearch — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • modlens — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)

sandbase-harness alternative? Top 6 similar tools

Looking for a sandbase-harness alternative? If you're comparing sandbase-harness with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcpproxy-go by smart-mcp-proxy · ⭐ 407

    Supercharge AI Agents, Safely

  • Containarium by FootprintAI · ⭐ 316

    Open-source agent runtime — SSH-native isolation, eBPF egress policy, Kubernetes + LXC backends, GPU passthrou

  • MCPJungle by mcpjungle · ⭐ 1.6k

    One place to manage & connect to all your MCP servers

  • memtrace-public by syncable-dev · ⭐ 511

    Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·

  • DashClaw by ucsandman · ⭐ 314

    Remote approvals, policy checks, and execution evidence for unattended AI agents.

  • metamcp by metatool-ai · ⭐ 2.7k

    MCP Aggregator, Orchestrator, Middleware, Gateway in one docker

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools