> ## Documentation Index > Fetch the complete documentation index at: https://docs.steerholm.ai/llms.txt > Use this file to discover all available pages before exploring further. # Introduction > An action plane for your agents. A control plane for you. Steerholm is one surface with two faces. To your AI agents it's an **action plane** — the single place they connect to and act. To you it's a **control plane** — where you decide what every agent can reach and do, down to the individual action and its arguments. Nothing runs that you didn't allow. New here? [Install Steerholm](/getting-started/installation), then the [quickstart](/getting-started/quickstart) gets you to a scoped agent in minutes. For the full mental model, see [the control plane](/concepts/control-plane).
Steerholm// ACTION PLANE
Claude Code
Cursor
Zed
VS Code
filesystem
git
database
shell
▸Claude Code→database
ACCESS POLICY(reaches 2/3 available tools)
R{"query"}{"sql=re:^SELECT"}
W{"execute"}{"sql=re:^INSERT"}

Agents and their servers connect through Steerholm. Every connection carries a policy you set — which tools, which arguments — and defaults to deny.

## Why it exists Today each agent configures its own MCP servers, with no shared management and no way to limit what an agent can do once it's connected. Steerholm brings them onto one plane you control: agents act in one place, and every action is checked against your policy before it reaches a server. ## Agents, servers, and grants The AI tools you govern — Claude Code, Cursor, VS Code, OpenCode. Each has a name, an access key, and a policy. The MCP servers you add. Each one exposes tools — the capabilities an agent might use. Scoped access from an agent to a server's tools — per tool, per argument. No grant means no access. Two things you **add** — agents and servers — and one governed connection you **grant** between them. See [Permissions](/concepts/permissions) for the tool and argument syntax. ## Set it up in three moves Register an MCP server once; the daemon starts and supervises it. ```bash theme={null} holm add server git --command "uvx mcp-server-git" ``` Register an agent and get its access key — the credential it connects with. ```bash theme={null} holm add agent coding-agent ``` Give the agent exactly the tools it needs, down to the argument. ```bash theme={null} holm grant coding-agent database --tool "query" --args "sql=re:^SELECT" ``` Then point the agent at `http://127.0.0.1:4767/mcp` with its access key — see [Add an agent](/guides/add-an-agent). It sees only the tools its policy allows.