sandbase-harness MCP Server
sandbaseai/sandbase-harness
[](https://agentrank-ai.com/tool/sandbaseai--sandbase-harness/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
sandbaseai/sandbase-harness is a TypeScript tool licensed under Apache-2.0. Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console. Topics: agent-observability, agent-runtime, ai-agents, deepseek-harness, mcp-server, model-context-protocol, agent-sandbox, ai-infrastructure, local-first, self-hosted, audit-logging, mcp-gateway, agent-harness, harness-engineering, sandboxed-execution, dsh-plugin, devops, docker, kubernetes, agent-plugin.
Ranked #368 out of 81417 indexed tools.
In the top 1% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
682 stars → growing community
Last commit today → actively maintained
139/158 issues closed → responsive maintainer
7 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
# SandBase Harness [English](./README.md) | [中文](./README.zh-CN.md) AI-readable project metadata: [llms.txt](./llms.txt) · [installation guide](./llms-install.md) 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. > Building with DeepSeek Harness? The independent [DeepSeek Harness Handbook](https://github.com/sandbaseai/deepseek-harness-handbook) provides source-backed runtime guides, multilingual troubleshooting, and a regularly updated [Agent-first resource map](https://sandbaseai.github.io/deepseek-harness-handbook/awesome-deepseek-harness-resources.html). > Looking for a lightweight bridge instead of a full runtime? [SandBase CLI](https://github.com/sandbaseai/cli) > connects 25 AI client targets to 2,000+ models and APIs through a local stdio MCP bridge. > If it fits your workflow, [star SandBase CLI](https://github.com/sandbaseai/cli/stargazers)Read full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.