Skip to content
Govern

How to Govern Claude-Powered Agents

Claude agents use tool calls and MCP integrations to take real-world actions. Cordum governs those actions before they execute.

The problem with ungoverned Claude Agents agents

  • Claude tool use lets agents call external APIs, modify databases, and send messages. Constitutional training helps but is not enforceable policy.
  • MCP servers expand Claude capability surface. Every new integration adds tools without governance.
  • Agent frameworks built on Claude execute multi-step tool chains. One unconstrained call causes cascading side effects.
  • No built-in approval workflow for Claude tool calls.

How Cordum governs Claude Agents

1

Route Claude agent tasks through Cordum

Submit Claude agent jobs via CAP v2. Safety Kernel evaluates every tool call against your policy bundle before dispatch.

const job = {
  type: "claude.agent.run",
  payload: {
    model: "claude-sonnet-4-6",
    tools: ["mcp:github", "mcp:slack", "file-write"],
    systemPrompt: agentPrompt,
    userMessage: taskDescription,
  },
};
await cordumClient.jobs.submit(job);
2

Govern MCP tool access

Define which MCP servers and tools each agent can use. Policies restrict access based on server, tool name, or context.

# Govern MCP tool usage
rules:
  - name: restrict-github-write
    match:
      tools_contains: "mcp:github"
      action_type: "write"
    action: REQUIRE_APPROVAL
    approvers: ["engineering-lead"]
  - name: allow-slack-read
    match:
      tools_contains: "mcp:slack"
    action: ALLOW
3

Pre-dispatch safety for tool chains

When a Claude agent plans a multi-step tool chain, Cordum evaluates the full plan before execution starts.

4

Full audit trail with MCP context

Every tool call, MCP interaction, and policy decision recorded in a structured timeline.

Claude Agents native vs Cordum governance

AreaClaude Agents NativeWith Cordum
Pre-dispatch tool governanceConstitutional training (soft constraint)Hard policy enforcement before execution
MCP access controlServer-level on/off onlyPer-tool, per-context policy rules
Approval workflowsNone built-inREQUIRE_APPROVAL with configurable approvers
Tool chain governanceNo multi-step policy checkingEvaluate full plan before execution
Audit trailAPI logsStructured run timeline with policy evidence

FAQ

Does Cordum work with Claude native tool use?

Yes. Cordum wraps the tool execution lifecycle. Claude decides which tools to call; Cordum ensures policy checks.

Can I use Cordum MCP server with Claude?

Yes. Cordum provides both stdio and HTTP/SSE MCP endpoints.

Related guides

Ready to govern your Claude Agents agents?

Start with the open-source Cordum platform. Add policies, approvals, and audit trails in minutes.