English Français العربية

Catalyst Governance

Official registry Security

Governance middleware for AI agents: permission gates, approvals, compliance scanning, audit ledger.

Source code Documentation

What can you do with Catalyst Governance?

  • Pre-execution permission gates with a progressive trust model: observe → advisory → proposal → strict
  • Human-in-the-loop approval flows — agents submit proposals, humans approve/decline
  • Compliance scanning across 8 frameworks: GDPR, SOC 2, ISO 27001, HIPAA, PCI-DSS, EU AI Act, Bribery Act, AML/KYC
  • Hash-linked audit ledger — every agent action is recorded with touched_by.source=mcp
  • Webhook notifications for proposal.accepted / proposal.declined events

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http catalyst-governance 'https://catalyst.stratogenic.ai/mcp' --header 'X-API-Key: <Your Catalyst API key from catalyst.stratogenic.ai>'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "catalyst-governance": {
            "type": "http",
            "url": "https://catalyst.stratogenic.ai/mcp",
            "headers": {
                "X-API-Key": "<Your Catalyst API key from catalyst.stratogenic.ai>"
            }
        }
    }
}
Remote (sse)
Claude Code 
claude mcp add --transport sse catalyst-governance 'https://catalyst.stratogenic.ai/mcp/sse' --header 'X-API-Key: <Your Catalyst API key from catalyst.stratogenic.ai>'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "catalyst-governance": {
            "type": "sse",
            "url": "https://catalyst.stratogenic.ai/mcp/sse",
            "headers": {
                "X-API-Key": "<Your Catalyst API key from catalyst.stratogenic.ai>"
            }
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Catalyst MCP Server
  2. What it does
  3. Use with Claude Code
  4. Connect
  5. Tools
  6. Governance loop
  7. Links

Catalyst MCP Server

Governance middleware for AI agents — hosted MCP server with both SSE and Streamable HTTP transports.

What it does

Catalyst puts a governance layer between your AI agent and consequential actions. Before your agent writes files, sends messages, deploys code, or calls external APIs, it checks in with Catalyst. Depending on your governance mode, actions are allowed, routed to a human for approval, or denied.

Core features:

  • Pre-execution permission gates with a progressive trust model: observe → advisory → proposal → strict
  • Human-in-the-loop approval flows — agents submit proposals, humans approve/decline
  • Compliance scanning across 8 frameworks: GDPR, SOC 2, ISO 27001, HIPAA, PCI-DSS, EU AI Act, Bribery Act, AML/KYC
  • Hash-linked audit ledger — every agent action is recorded with touched_by.source=mcp
  • Webhook notifications for proposal.accepted / proposal.declined events

Use with Claude Code

Claude Code is a primary use case Catalyst was designed for. Claude Code governs itself session-locally — it asks before running dangerous commands, but those decisions leave no audit trail, survive no context reset, and sit outside your organisation's approval workflows.

Catalyst externalises that governance. Once connected, every consequential action Claude Code attempts is routed through your policy, logged in an immutable ledger, and (if required) held for human approval in the Catalyst dashboard before Claude Code proceeds.

Connect in one command:

claude mcp add catalyst \
  --transport sse \
  --url https://catalyst.stratogenic.ai/mcp/sse \
  --header "X-API-Key: SGC_your_key_here"

Or with Streamable HTTP (Claude Code 0.10+):

claude mcp add catalyst \
  --transport http \
  --url https://catalyst.stratogenic.ai/mcp \
  --header "X-API-Key: SGC_your_key_here"

Claude Code will automatically call catalyst_check_action before destructive operations and catalyst_await_approval when a proposal is required. Every action is ledgered with touched_by.source=mcp — you get a permanent, verifiable record of what your AI coding agent did and when.

What governance looks like in practice:

Claude Code actionCatalyst response (proposal mode)
git push --forceproposal_required — held for approval
rm -rf ./distallow — whitelisted build action
Deploy to productionproposal_required — held for approval
Edit source filesallow — within declared capabilities
Call external APIproposal_required — undeclared capability

Set your governance mode to observe to start with a full audit trail only, advisory to flag deviations without blocking, proposal to require human sign-off on sensitive actions, or strict to allow only explicitly whitelisted capabilities.

Get your API key at catalyst.stratogenic.ai.

Connect

Streamable HTTP (preferred — required by Glama, Smithery, and newer clients):

{
  "mcpServers": {
    "catalyst": {
      "url": "https://catalyst.stratogenic.ai/mcp",
      "transport": "http",
      "headers": { "X-API-Key": "<your-key>" }
    }
  }
}

SSE (for clients that don't yet support Streamable HTTP):

{
  "mcpServers": {
    "catalyst": {
      "url": "https://catalyst.stratogenic.ai/mcp/sse",
      "transport": "sse",
      "headers": { "X-API-Key": "<your-key>" }
    }
  }
}

Get your API key at catalyst.stratogenic.ai.

Tools

ToolDescription
catalyst_my_governanceShow your governance profile and plan capabilities
catalyst_check_actionCheck if a capability is permitted before acting
catalyst_log_taskRecord a task or action into the governance pipeline
catalyst_pending_approvalsList proposals awaiting human sign-off
catalyst_await_approvalPoll a specific proposal's approval status
catalyst_register_approval_webhookRegister a callback URL for approval events
catalyst_run_compliance_scanRun an automated compliance scan (requires add-on)
catalyst_list_compliance_frameworksList available compliance frameworks
catalyst_get_dashboardGet the governance dashboard snapshot
catalyst_export_ledgerExport the hash-linked audit chain

Governance loop

catalyst_my_governance()            # understand your mode + capabilities
    ↓
catalyst_check_action("write_file") # allow | proposal_required | deny
    ↓ if proposal_required
catalyst_log_task("Deploy to prod") # creates proposal, returns proposal_id
    ↓
catalyst_await_approval(proposal_id) # poll until approved: true
    ↓ proceed

Frequently asked questions

What is Catalyst Governance?

Governance middleware for AI agents: permission gates, approvals, compliance scanning, audit ledger.

How do I install Catalyst Governance?

It runs as a remote server. In Claude Code: claude mcp add --transport http catalyst-governance 'https://catalyst.stratogenic.ai/mcp' --header 'X-API-Key: <Your Catalyst API key from catalyst.stratogenic.ai>'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Catalyst Governance need an API key?

Yes. It expects X-API-Key, which you set in its configuration.

Is Catalyst Governance open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Catalyst Governance?

It is published by Stratogenic-AI. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.