{"id":"co.promptguard/security","slug":"co-promptguard-security","title":"PromptGuard","description":"Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client","version":"1.2.5","publisher":{"kind":"domain","id":"promptguard.co","label":"promptguard.co","url":"https://promptguard.co"},"website":"https://promptguard.co","repository":"https://github.com/promptguardhq/promptguard","remotes":[{"type":"streamable-http","url":"https://api.promptguard.co/mcp"}],"packages":[{"registryType":"npm","identifier":"@promptguard/mcp-server","version":"1.2.5","transport":{"type":"stdio"},"environmentVariables":[{"description":"PromptGuard API key (starts with pg_live_)","format":"string","isSecret":true,"name":"PROMPTGUARD_API_KEY"}]},{"registryType":"oci","identifier":"ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5","transport":{"type":"stdio"},"environmentVariables":[{"description":"PromptGuard API key (starts with pg_live_)","format":"string","isSecret":true,"name":"PROMPTGUARD_API_KEY"}]}],"published":"2026-11-13","updated":"2026-11-13","status":"online","auth":"","latency_ms":918,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"promptguard_scan_text","title":"Scan text for threats","description":"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.\nWhen to use: When reviewing user-facing prompts, testing LLM inputs for safety, or verifying that content is free of injection attacks before sending to an LLM.","read_only":true},{"name":"promptguard_scan_code","title":"Find LLM SDK calls in code","description":"Analyze code for LLM SDK usage patterns (OpenAI, Anthropic, Cohere, Google Gemini, Bedrock). Detects import statements and client instantiations via pattern matching.\nWhen to use: After generating new code that uses LLM SDKs, when reviewing pull requests, or when auditing a codebase for security coverage gaps.","read_only":true},{"name":"promptguard_redact","title":"Redact PII","description":"Redact PII from text. Returns the text with each entity replaced by a labeled placeholder, e.g. [EMAIL_REDACTED], [PHONE_REDACTED], [SSN_REDACTED], the PII types found, and `skipped`: the matches deliberately left in the text. Never returns the original text. Each call counts as one Request on your PromptGuard plan.\nWithout `pii_types` it redacts what the Project's policy redacts; a default Projec","read_only":true},{"name":"promptguard_status","title":"PromptGuard status","description":"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).\nWhen to use: To verify PromptGuard is properly configured, or to confirm which version is running.","read_only":true},{"name":"promptguard_list_events","title":"List security events","description":"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 first, at most 50. Filter by decision, threat type, project (by id, or by the name the User gave) or a start time. Only PromptGuard's own values are returned: never ","read_only":true},{"name":"promptguard_get_usage","title":"Get usage this month","description":"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.\nWhen to use: To check whether the account is close to its plan limit.","read_only":true},{"name":"promptguard_list_policies","title":"List policies","description":"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. Names and descriptions in the result are free text your organization recorded in PromptGuard.\nWhen to use: To see which protections are configured before explaining a block, o","read_only":true},{"name":"promptguard_list_audit_log","title":"List audit log entries","description":"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. Read-only. Names and descriptions in the result are free text your organization recorded in PromptGuard.\nWhen to use: To answer who changed a setting or key, an","read_only":true},{"name":"promptguard_list_projects","title":"List projects and their configuration","description":"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, never the URL). No keys or secrets. Read-only. Names and descriptions in the result are free text your organization recorded in PromptGuard.\nWhen to use: To che","read_only":true},{"name":"promptguard_get_fleet_status","title":"Get Shadow AI fleet status","description":"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 seen. Needs an organization admin. No enrollment tokens or keys. Read-only. Names and descriptions in the result are free text your organization recorded in Prom","read_only":true},{"name":"promptguard_list_red_team_tests","title":"List red-team tests","description":"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 tests; it runs nothing. Read-only.\nWhen to use: To explain what security testing covers before running it.","read_only":true},{"name":"promptguard_list_webhook_deliveries","title":"List webhook deliveries","description":"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's response. Read-only.\nWhen to use: To check whether alerts are reaching their destination.","read_only":true},{"name":"promptguard_propose_suppression","title":"Suppress a rule on a project","description":"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.detector and rule.id, e.g. from an event).\nConfirmation: in the PromptGuard dashboard this returns a Proposal the User confirms or dismisses in the panel, within","read_only":false}],"server_info":{"name":"promptguard","version":"3.52.2","websiteUrl":"https://promptguard.co","icons":[{"src":"https://promptguard.co/logo.svg","mimeType":"image/svg+xml","sizes":["any"],"theme":"light"},{"src":"https://promptguard.co/logo-on-dark.svg","mimeType":"image/svg+xml","sizes":["any"],"theme":"dark"},{"src":"https://promptguard.co/logo-512.png","mimeType":"image/png","sizes":["512x512"]}]},"category":"agents","tags":["developer","security","automation"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-04-05","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/co-promptguard-security/"}