Other · Local MCP server

SandBase Harness

Stdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.sandbaseai/sandbase-harness
Version
0.3.8
Status
Active
Category
other
Transport
stdio (local process)
Package
OCI image (Docker)
Published
2026-08-30
Updated
2026-08-30
Publisher
sandbaseai (GitHub) · 2 servers with pages here
Repository
github.com/sandbaseai/sandbase-harness
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
OCI image (Docker)ghcr.io/sandbaseai/sandbase-harness-mcp:0.3.8—stdioMANAGED_AGENTS_URL (required), MANAGED_AGENTS_API_KEY (secret)

How to connect SandBase Harness

SandBase Harness runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/sandbaseai/sandbase-harness-mcp:0.3.8. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm -e MANAGED_AGENTS_URL -e MANAGED_AGENTS_API_KEY ghcr.io/sandbaseai/sandbase-harness-mcp:0.3.8. It reads these environment variables: MANAGED_AGENTS_URL (required) and MANAGED_AGENTS_API_KEY (secret); set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "sandbase-harness": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MANAGED_AGENTS_URL",
        "-e",
        "MANAGED_AGENTS_API_KEY",
        "ghcr.io/sandbaseai/sandbase-harness-mcp:0.3.8"
      ],
      "env": {
        "MANAGED_AGENTS_URL": "<value>",
        "MANAGED_AGENTS_API_KEY": "<secret>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from sandbaseai (GitHub)

ServerRunsEndpoint or package
SandBaseConnect MCP clients to 2,000+ AI models without managing provider API keys.Remote · HTTPsandbase.ai

More other servers

All 6,730 →
ServerRunsEndpoint or package
SanctionScreenScreen counterparties and enrich companies for AI agents — sanctions checks, cited sources.Remote · HTTPapi.sanctionsscreen.io
SanctionwiseVerified UK sanctions screening for AI agents — official FCDO UK Sanctions List, not guesses.Local · stdionpm: sanctionwise
SanctuaryScripture prayers and a safe house-church finder for people who left church but kept the faith.Remote · HTTPsanctuary-mcp.vercel.app
SanctumAI — Credential Vault for AI AgentsCredential vault for AI agents — encrypted storage, lease-based access, CRP support.Local · stdionpm: @sanctumai/mcp-server
Sandbox as a ServiceGive an agent a real Linux VM: run commands, move files, expose a preview URL, destroy it.Local · stdioMCP Bundle (.mcpb): fstandhartinger/sandbox-as-a-service-mcp/release
Sandwich Care CircleAuthenticated MCP for a user's care circle: read CareEvents, list loved ones, inspect workspace.Remote · HTTPapp.joinsandwich.com
SAP SuccessFactorsSAP SuccessFactors OData and Compound Employee queries with PII tokenization for AI agents.Local · stdioOCI image (Docker): docker.io/wudaoyou/successfactors-toolkit:v0.5.5
SaperlyPhone carrier for AI agents. Provision numbers, make calls, send SMS, TCPA compliance built-in.Local · stdionpm: @saperly/mcp