Side-by-Side Model Context Protocol Comparison
Agentguard vs Platform
In-depth architectural comparison of the Agentguard and Platform MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Agentguard
Security · Remote HTTP/SSE
Quality: 51/100 (Good) | Auth: No auth required
Platform
Security · Local stdio
Quality: 56/100 (Good) | Auth: API Key required
Verdict Summary: Choose Agentguard if you need specialized Security tools running via a hosted cloud SSE transport. Choose Platform if your workspace requires Security integration with local subprocess execution. Both servers can be configured concurrently in your client's
mcpServers manifest.Which MCP Server Should You Choose?
Choose Agentguard when:
- You need dedicated capabilities in the Security domain.
- You prefer remote streaming HTTP/SSE transport architecture.
- Your security boundary fits: No auth required (Free / Open Source).
- Primary tools included: policy_preflight, tool_risk_score, approval_required.
Choose Platform when:
- You need dedicated capabilities in the Security domain.
- You prefer local stdio subprocess transport architecture.
- Your security boundary fits: API Key required (Free / Open Source).
- You have access to required keys:
SIDCLAW_API_KEY, SIDCLAW_AGENT_ID. - Primary tools included: MCP governance proxy, Policy-based allow, deny, and approval decisions, Human review workflows.
Feature & Specification Comparison
Tools & Capabilities Breakdown
Agentguard Tools (7)
policy_preflight
Pre-flight check before any tool call. Evaluates 7 policies, computes risk score, detects threats, auto-logs. Returns `allowed`/`denied`/`require_approval`/`flagged`.
tool_risk_score
0-100 risk score for tool + input. Detects secrets (API keys, passwords), prompt injection, high-value amounts. `eth_gas`→5, `payment_execute`→95+.
approval_required
Check if tool needs human approval. Optionally registers a pending approval request with tracking URL.
audit_log_write
Write tool execution to persistent, cryptographically-signed audit log (SQLite WAL). Call after execution to record outcome.
audit_log_query
Query audit trail. Filter by agent, tool, decision, time range. Paginated. Returns signed entries for tamper verification.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Agentguard Configuration
Platform Configuration
