toolhive MCP — Use Cases, Install & Live Demo

Why use it

Key features

Container-isolated MCP servers (Docker / Kubernetes)
Curated, verified MCP registry with preset configs
One-click install into Claude Desktop, Cursor, VS Code
SSO, encrypted secrets, audit logging, OpenTelemetry
Desktop app, web, CLI, and Kubernetes Operator

Live Demo

What it looks like in practice

toolhive.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "toolhive": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/stacklok/toolhive"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "toolhive": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/stacklok/toolhive"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "toolhive": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/stacklok/toolhive"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "toolhive": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/stacklok/toolhive"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "toolhive",
      "command": "TODO",
      "args": [
        "See README: https://github.com/stacklok/toolhive"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "toolhive": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/stacklok/toolhive"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add toolhive -- TODO 'See README: https://github.com/stacklok/toolhive'

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use toolhive

How to install a community MCP without trusting random `npx -y` scripts

👤 Security-conscious engineers ⏱ ~10 min beginner

When to use: You want the GitHub MCP running locally but don't want to give it unrestricted filesystem access.

Prerequisites

Docker Desktop — docker.com
ToolHive desktop app — stacklok.com/download

Flow

Open ToolHive, search the registry

Install 'github' from the ToolHive registry.✓ Copied

→ Container pulled, config prompt for GITHUB_TOKEN
Auto-configure your client

Click 'Connect to Claude Desktop'.✓ Copied

→ Claude Desktop config updated; restart required
Verify isolation

Confirm the container only has the env vars you set and no host filesystem mounts.✓ Copied

→ Inspect container config in the ToolHive UI

Outcome: A sandboxed MCP with least-privilege access to your machine.

Pitfalls

Filesystem MCPs need a mount — default no-mount is too tight — Add a scoped mount (e.g. ~/Projects only) rather than full-home

How to deploy MCPs on Kubernetes for a platform team

👤 Platform engineers ⏱ ~60 min advanced

When to use: You want org-wide standardized MCP availability.

Prerequisites

Kubernetes cluster + cluster-admin — Existing EKS/GKE/AKS or kind for dev
ToolHive Operator CRDs installed — kubectl apply -f the Stacklok-provided manifests

Flow

Declare MCPServer resources

kubectl apply -f mcp-github.yaml — declaratively register a GitHub MCP with scoped secrets.✓ Copied

→ Pod running; Portal lists it
Expose to users via Portal

Engineers log into the Portal with SSO and one-click install into their client.✓ Copied

→ Per-user configs auto-generated

Outcome: Central catalog + per-user install; auditable.

Pitfalls

Stdio MCPs don't fit network-exposed Kubernetes well — Prefer Streamable HTTP MCPs for k8s; use the gateway for stdio ones

How to produce an audit trail of all MCP tool calls

👤 Compliance, security teams ⏱ ~30 min intermediate

When to use: Your org needs 'who called what tool when' for SOC2 or internal policy.

Flow

Enable OpenTelemetry export

In ToolHive settings, set the OTLP endpoint to your collector.✓ Copied

→ Traces appear in your backend
Tag by user

Enable per-user identity propagation via SSO.✓ Copied

→ Each trace has actor id

Outcome: Per-user, per-tool audit log.

Combinations

Pair with other MCPs for X10 leverage

toolhive + mcphub

Use ToolHive for isolation, MCPHub for multi-server routing

Run each MCP in its own ToolHive container and expose them through MCPHub groups.✓ Copied

toolhive + unla

Combine ToolHive-run MCPs with Unla's REST-to-MCP conversion

Register our Unla-converted internal API in ToolHive so it runs containerized with SSO.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
(platform) registry-install	mcp_name	Install a verified MCP	free
(platform) gateway-proxy	Transport + auth policy	Front your MCPs with policy	free
(platform) runtime-isolate	Container spec	Sandboxed execution	free + infra cost

Cost & Limits

What this costs to run

API quota: None at platform layer
Tokens per call: Minimal overhead
Monetary: Desktop + CLI + open-source Operator are free. Enterprise plans for support/compliance.
Tip: Start with the free tier; upgrade only if you need dedicated SLAs or advanced SSO/RBAC.

Security

Permissions, secrets, blast radius

Minimum scopes: Per-MCP: least privilege env vars and mounts SSO for team deployments

Credential storage: Encrypted secrets manager built into ToolHive

Data egress: Determined by downstream MCPs; ToolHive adds telemetry if configured

Never grant: Don't auto-grant filesystem mounts beyond what each MCP needs

Running too many MCPs in a single container defeats the isolation; one per container.

Troubleshooting

Common errors and fixes

Container starts then exits immediately

Check the MCP's required env vars are set (e.g., GITHUB_TOKEN). View logs in ToolHive UI.

Claude Desktop can't find the server after install

Restart Claude Desktop — config changes only load on launch.

K8s Operator CRD install fails

Ensure cluster-admin and supported k8s version (>= 1.27).

Verify: kubectl version

OTLP traces missing

Collector endpoint must accept OTLP/HTTP or OTLP/gRPC; confirm protocol match.

Alternatives

toolhive vs others

Alternative	When to use it instead	Tradeoff
MCPHub	You want multi-server aggregation more than container isolation	Not container-runtime focused
Docker MCP Toolkit	You prefer Docker's own integrated tooling	Less curated registry

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills