PromptGuard
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
Reviews
No review yet. Used PromptGuard? Be the first to help others choose.What it does
PromptGuard is an MCP server, a connector that lets an AI assistant use it as a tool. It can be used hosted (nothing to install) or installed locally.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 2d ago (live check)Hosted endpoint
https://api.promptguard.co/mcpstreamable-http
In Claude Code: claude mcp add --transport http promptguard https://api.promptguard.co/mcp
Install packages
- NPM
@promptguard/mcp-serverv1.2.5 · runs locally (stdio) - DOCKER
ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5· runs locally (stdio)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"promptguard": {
"url": "https://api.promptguard.co/mcp"
}
}
}Live check
Electra Index connected to the hosted endpoint 2d agoONLINE PromptGuard answered an MCP connection on 11 Nov 2026 and introduced itself as promptguard 3.49.0 (MCP protocol 2025-06-18).
13 tools offered to AI assistants
promptguard_scan_text· Scan text for security threats including prompt injection, jailbreaks, PII leakage, and toxic content. Returns a decision (allow/block), confidence score, threat type, and reason. Each call counts as one Request on your PromptGuard plan. Whpromptguard_scan_code· Analyze code for LLM SDK usage patterns (OpenAI, Anthropic, Cohere, Google Gemini, Bedrock). Detects import statements and client instantiations via pattern matching. When to use: After generating new code that uses LLM SDKs, when reviewingpromptguard_redact· Redact PII (emails, phone numbers, SSNs, credit cards, API keys) from text. Returns sanitized text with each entity replaced by a labeled placeholder, e.g. [EMAIL_REDACTED], [PHONE_REDACTED], [SSN_REDACTED], and the PII types found. Never rpromptguard_status· Show whether PromptGuard is set up and signed in, with this server's version and the account or configuration details it knows (the hosted server reports your plan; the local CLI server reports its key type, proxy URL and providers). When tpromptguard_list_events· List your organization's most recent PromptGuard security events: what was blocked, redacted, flagged or allowed, with the threat types, confidence, direction, surface, provider, project id and each finding's detector and rule. Newest firstpromptguard_get_usage· Show this billing month's PromptGuard usage against your plan: Requests used and remaining, the monthly limit, usage credit where the plan has one, and the days until it resets. Read-only. When to use: To check whether the account is closepromptguard_list_policies· List your organization's PromptGuard security policies across every project: name, type, whether it is active and enforced, its priority and threat types, and how often it has triggered. Read-only; it cannot change a policy. Text in the respromptguard_list_audit_log· List recent entries in your organization's PromptGuard audit trail (who changed what, sign-ins, key and policy changes), newest first, at most 50. Filter by category, action, severity, outcome or a start time. Needs a plan with audit logs.promptguard_list_projects· List the PromptGuard projects you are shown in your organization and how each is configured: strictness, fail mode, enforcement mode, zero retention, agent policy enforcement, and whether alerts go to a webhook or alert channels (the kind,promptguard_get_fleet_status· Show your organization's Shadow AI fleet: whether Shadow AI is required, its mode and fail-closed setting, how many Devices are active or revoked, and for each Device its platform, agent version, coverage, proxy state and when it was last spromptguard_list_red_team_tests· List the attacks PromptGuard's security testing (red team) runs against a project's guardrails: each test's name, category, what it tries and the result expected, and whether your organization's plan includes running them. It lists the testpromptguard_list_webhook_deliveries· List recent alert deliveries to your projects' webhooks and alert channels, newest first, at most 50: whether each was delivered, is pending or failed, its attempts and the receiver's HTTP status. Never the payload, the URL or the receiver'
Show 1 more
promptguard_propose_suppression· Suppress one rule of one detector on one project until it expires: the rule stops deciding the project's requests, and its findings are still recorded, marked suppressed. Name the project by its id and the rule as a finding names it (rule.d
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Install package | @promptguard/mcp-server, ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5 | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Version | 1.2.5 | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Website | https://promptguard.co | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Hosted endpoint | https://api.promptguard.co/mcp | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Repository | https://github.com/promptguardhq/promptguard | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Package registries | npm, oci | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Local install (package) | yes | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 21h ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 21h ago |
Change history
- VERSION13 Nov 20261.2.4 → 1.2.5
- VERSION10 Nov 20261.2.3 → 1.2.4
- VERSION05 Nov 20261.2.2 → 1.2.3
- VERSION05 Nov 20261.2.1 → 1.2.2
- VERSION05 Nov 20261.2.0 → 1.2.1
- CHANGED04 Nov 2026remote access: no → yes
- VERSION04 Nov 20261.1.3 → 1.2.0
- VERSION01 Nov 20261.1.2 → 1.1.3
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is PromptGuard still online?
Free alerts · no account▲ 0Do you run PromptGuard? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about PromptGuard
How do I connect PromptGuard?
Use the hosted endpoint https://api.promptguard.co/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
What tools does PromptGuard offer?
When Electra Index connected on 11 Nov 2026, it listed 13 tools: promptguard_scan_text, promptguard_scan_code, promptguard_redact, promptguard_status, promptguard_list_events, promptguard_get_usage, promptguard_list_policies, promptguard_list_audit_log and more. The full list is in "Live check" above.
Is PromptGuard online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 2d ago.