Agent Security Scanner MCP vs Agentguard
A side-by-side look at the Agent Security Scanner MCP and Agentguard MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Security Scanner MCP for security work as a local process; choose Agentguard for security. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agent Security Scanner MCP when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- You want tools like
scan_security, fix_security, record_security_outcome.
Choose Agentguard when
- You need dedicated capabilities in the Security domain.
- You want tools like
policy_preflight, tool_risk_score, approval_required.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Security | Security |
| Quality signal | 68/100 · Great | 39/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 124 | 0 |
| Directory activity | 2 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 23 | 7 |
| Full listing | View Agent Security Scanner MCP | View Agentguard |
Tools & capabilities
Agent Security Scanner MCP tools 23
scan_securityScan a file for security vulnerabilities. Use verbosity='minimal' for counts only (~50 tokens), 'compact' (default) for actionable info (~200 tokens), 'full' for complete metadata.fix_securityScan a file and return fixes. Use verbosity='minimal' for summary only, 'compact' (default) for fix list, 'full' for complete fixed file content.record_security_outcomeRecord aggregate remediation outcomes after reviewing scanner findings. Sends counts only; never sends code, findings, paths, or rule IDs.list_security_rulesList all available security fix templates and their descriptionscheck_packageCheck if a package name is legitimate or potentially hallucinated (AI-invented)scan_packagesScan code for package imports and check for hallucinated (AI-invented) packages. Use verbosity='minimal' for counts, 'compact' (default) for flagged packages, 'full' for all details.list_package_statsList statistics about loaded package lists for hallucination detectionscan_agent_promptScan a prompt for malicious intent. Returns BLOCK/WARN/LOG/ALLOW. Use verbosity='minimal' for action only, 'compact' (default) for findings, 'full' for audit details.scan_git_diffScan git diff for new security vulnerabilities. Only reports issues on changed lines. Use for PR reviews.scan_projectScan an entire directory for security vulnerabilities with .gitignore support and security grading. Use verbosity='minimal' for grade + counts, 'compact' (default) for top issues, 'full' for all details.scan_agent_actionPre-execution security check for agent actions (bash, file_write, file_read, http_request, file_delete, cron, process_spawn, git, docker). Returns ALLOW/WARN/BLOCK.scan_mcp_serverScan an MCP server's source code for security vulnerabilities: overly broad permissions, missing input validation, data exfiltration, insecure patterns. Returns grade (A-F) and recommendations.- +11 more on the listing page
Agentguard tools 7
policy_preflightPre-flight check before any tool call. Evaluates 7 policies, computes risk score, detects threats, auto-logs. Returns `allowed`/`denied`/`require_approval`/`flagged`.tool_risk_score0-100 risk score for tool + input. Detects secrets (API keys, passwords), prompt injection, high-value amounts. `eth_gas`→5, `payment_execute`→95+.approval_requiredCheck if tool needs human approval. Optionally registers a pending approval request with tracking URL.audit_log_writeWrite tool execution to persistent, cryptographically-signed audit log (SQLite WAL). Call after execution to record outcome.audit_log_queryQuery audit trail. Filter by agent, tool, decision, time range. Paginated. Returns signed entries for tamper verification.decision_explainHuman-readable explanation of any allow/deny decision. Pass `request_id` for stored entry or `tool_name` + `tool_args` for fresh analysis.rate_limit_checkCheck agent rate limits: 200/min, 5000/hr, 50000/day. Returns per-window usage with percentage.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agent Security Scanner MCP
{
"mcpServers": {
"agent-security-scanner-mcp": {
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}
Agentguard
No confirmed install command for Agentguard yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Agent Security Scanner MCP is categorized under Security and uses a local stdio subprocess. Agentguard belongs to Security and uses an install path we have not confirmed yet. Pick Agent Security Scanner MCP for security work and Agentguard for security.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Agentguard has no confirmed install command yet — follow its own setup instructions.
Agent Security Scanner MCP has no declared pricing — check the project's own site. Agentguard has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add agent-security-scanner-mcp and agentguard-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Security Scanner MCP has a quality signal of 68/100 (Great) with 2 views, 0 installs and 124 GitHub stars. Agentguard has 39/100 (Fair) with 2 views, 0 installs and 0 GitHub stars.