workflow-guard-mcp
Provides OpenAI Codex with a shared policy decision point for proposed shell, file write, git, and network actions, returning allow, deny, or ask verdicts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@workflow-guard-mcp Check if this action is allowed: git push --force"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
workflow-guard-mcp
Portable guardrails for agentic coding clients that speak the Model Context Protocol (MCP).
The project is intended to reduce the blast radius of fast, highly autonomous coding workflows by giving clients a shared policy decision point. The MCP server does not execute the proposed action itself.
Status
This repository is an early scaffold. The current guard_check tool demonstrates a stable policy-decision contract; it is not yet a complete port of opencode-workflow-guard policies.
Most importantly, connecting an MCP server does not make it an interceptor for every native tool a coding client can execute. Hard enforcement depends on integration support in the host. See Compatibility and Plan.
Related MCP server: Laguarde
Tools
guard_check: evaluates a proposedshell,file_write,git, ornetworkaction and returnsallow,deny, oraskwith a machine-readable policy ID.guard_status: reports the server's current enforcement mode. It explicitly identifies this scaffold as host-dependent policy advice.
Development
Requires Node.js 20 or newer.
npm install
npm test
npm run typecheck
npm run buildThe initial transport is stdio because both Claude Code and Codex support local stdio MCP servers. Streamable HTTP can be added without changing the policy API.
Design Principle
The public promise is deliberately narrower than "this MCP sandboxes your coding agent." It centralizes policy. Client adapters enforce that policy wherever the client exposes a trustworthy interception mechanism; otherwise the result remains advisory and should be combined with the client's native sandbox and approval controls.
Sources
The compatibility design was checked against current official documentation and source on 2026-08-27:
Anthropic Claude Code MCP: https://docs.claude.com/en/docs/claude-code/mcp
Anthropic Claude Code hooks: https://github.com/anthropics/claude-code/blob/main/plugins/plugin-dev/skills/hook-development/SKILL.md
OpenAI Codex: https://github.com/openai/codex
Codex MCP configuration implementation: https://github.com/openai/codex/blob/main/codex-rs/config/src/mcp_types.rs
MCP TypeScript SDK: https://github.com/modelcontextprotocol/typescript-sdk/blob/v1.29.0/docs/server.md
License
MIT
Available Tools
2 toolsguard_checkB
Evaluate a proposed coding-agent action. Advisory unless the host wires the result into enforcement.
Inputs: action (required), path, command.
guard_statusA
Report guard capabilities and the enforcement boundary.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
guard_check and guard_status have clearly distinct purposes: one evaluates an action, the other reports capabilities and enforcement boundaries. There is no overlap or ambiguity between them.
Both tools follow a consistent guard_ prefix with lowercase underscore naming. The pattern is uniform and predictable.
With only 2 tools, the server feels thin even for its narrow purpose. The count is borderline, sitting at the low end of what might be considered a minimal but workable surface.
The two tools cover the core guard workflow (evaluate action, check status) with only minor gaps like listing specific rules or explaining decisions. Agents can likely work around these by using the provided tools.
Maintenance
Related MCP Connectors
Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnforces deterministic policies on AI agent tool calls, evaluating actions against compliance modules (SOC 2, HIPAA, GDPR, etc.) and returning ALLOW, BLOCK, or CONSTRAIN decisions with an audit trail.MIT- FlicenseNot gradedqualityDmaintenanceEnables AI coding agents to evaluate actions against team-defined policies, record decisions, and obtain human approvals for potentially risky operations.63 npm1-

agentguardofficial
AlicenseNot gradedqualityAmaintenanceEnforces policy controls for AI agents, including spend limits, action approvals, kill switch, scoped credentials, dry-run diffs, loop prevention, and auditable hash-chained logs.MIT
ERDL Guardofficial
AlicenseNot gradedqualityBmaintenanceEnforces deterministic policy decisions on AI agent tool calls, supporting allow, deny, correct, escalate, and human review actions with verifiable audit receipts.MIT