Catalyst - AI Agent Governance
Governance middleware for AI agents.
What it can do
- Catalyst My Governance: Show the current agent governance profile, risk class, and capabilities.
- Catalyst Check Action: Pre-execution gate for consequential agent actions. Returns allow, proposal_required, or deny.
- Catalyst Log Task: Record work or agent decisions into the governed task pipeline and audit ledger.
What data it sees
Do you need an account
No: the server works without sign-in
Governance middleware for AI agents. Pre-execution permission gates with a progressive trust model (observe → advisory → proposal → strict), human-in-the-loop approval flows, compliance scanning across 8 frameworks (GDPR, SOC 2, ISO 27001, HIPAA, PCI-DSS, EU AI Act, Bribery Act, AML/KYC), and a hash-linked audit ledger.
Connect once with your API key — no per-call auth needed. Works with Claude Code, Claude Desktop, and any MCP-compatible agent runtime.
How to connect
How to connect Catalyst - AI Agent Governance to Claude
The server address to paste into Claude settings:
https://catalyst--markjsmith311.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Catalyst - AI Agent Governance to ChatGPT
The server address to paste into ChatGPT settings:
https://catalyst--markjsmith311.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Catalyst - AI Agent Governance to Cursor
The server address to paste into Cursor settings:
https://catalyst--markjsmith311.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (31)
Raw names from tools/list. Only developers need these.
| catalyst_my_governance | Show the current agent governance profile, risk class, and capabilities. |
| catalyst_check_action | Pre-execution gate for consequential agent actions. Returns allow, proposal_required, or deny. |
| catalyst_log_task | Record work or agent decisions into the governed task pipeline and audit ledger. |
| catalyst_pending_approvals | List proposals awaiting human approval. |
| catalyst_await_approval | Check whether a specific proposal has been approved before proceeding. |
| catalyst_register_approval_webhook | Register a callback URL to receive proposal approval and decline notifications. |
| catalyst_ingest_task | Ingest one or more tasks into the deterministic governance kernel. |
| catalyst_search_tasks | Search governed tasks by query, domain, or priority. |
| catalyst_update_task | Update a task with ledger-recorded provenance. |
| catalyst_bulk_update_tasks | Bulk update tasks matching a filter. Plan-gated. |
| catalyst_list_proposals | List pending proposals awaiting a governance decision. |
| catalyst_accept_proposals | Accept proposals and commit them into the live flow cycle. |
| catalyst_decline_proposals | Decline proposals and record the decision for audit and learning. |
| catalyst_review_proposal | Approve or reject a review-required proposal. |
| catalyst_get_graph_views | Return the governance graph views for the tenant. |
| catalyst_get_dashboard | Return the tenant governance dashboard snapshot. |
| catalyst_get_org_summary | Return an AI-safe organisational execution summary. |
| catalyst_run_compliance_scan | Run deterministic compliance evaluation. |
| catalyst_get_compliance_findings | Return current compliance findings. |
| catalyst_create_tasks_from_findings | Create remediation tasks from compliance findings. |
| catalyst_list_compliance_frameworks | List available compliance framework packs. |
| catalyst_activate_compliance_framework | Activate a compliance framework pack. |
| catalyst_list_compliance_rules | List effective compliance rules. |
| catalyst_register_machine_actor | Register an AI agent or automation actor. |
| catalyst_evaluate_agent_action | Evaluate a machine actor action against governance policy. |
| catalyst_register_workflow | Register an AI workflow with risk and oversight metadata. |
| catalyst_send_lite_event | Record an AI workflow lifecycle event. |
| catalyst_get_workflow_trust | Return the deterministic trust score for an AI workflow. |
| catalyst_export_workflow_audit | Export an AI workflow audit log. |
| catalyst_weekly_summary | Return a deterministic seven-day activity rollup. |
| catalyst_export_ledger | Export the hash-linked audit ledger. |