{"data":{"name":"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","websiteUrl":"https://promptguard.co","repositoryUrl":"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","runtimeHint":"stdio","runtimeArguments":null,"environmentVariables":null},{"registryType":"oci","identifier":"ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5","version":null,"runtimeHint":"stdio","runtimeArguments":null,"environmentVariables":null}],"status":"active","isLatest":true,"publishedAt":"2026-11-13T03:36:26.827Z","updatedAt":"2026-11-13T03:36:26.827Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"source":"official-registry","sourceId":"co.promptguard/security","verification":"official","confidence":100,"stars":null,"updatedAt":"2026-11-13T03:36:26.827Z","title":"PromptGuard","description":"Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client","websiteUrl":"https://promptguard.co","repositoryUrl":"https://github.com/promptguardhq/promptguard"}],"toolIndex":{"tools":[{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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 PromptGuard.\nWhen to use: To find Devices that stopped reporting or run an old agent.","inputSchema":{"type":"object","properties":{"limit":{"default":20,"description":"How many Devices to list","maximum":50,"minimum":1,"type":"integer"}},"additionalProperties":false},"annotations":{"title":"Get Shadow AI fleet status","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"3c47ea1b1d5e00b7119b0674ae2b9074838f51add26b8759aab8f39f557528a4","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{},"additionalProperties":false},"annotations":{"title":"Get usage this month","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"a5f486e8e57056212371b238466d2833ce511abb08e41c9097ef510c5c664786","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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, and when.","inputSchema":{"type":"object","properties":{"category":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only this category"},"action":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only this action"},"severity":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only this severity"},"outcome":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only this outcome"},"since":{"anyOf":[{"format":"date-time","type":"string"},{"type":"null"}],"default":null,"description":"Only entries at or after this time (ISO 8601; UTC if no zone)"},"limit":{"default":20,"description":"How many entries to return","maximum":50,"minimum":1,"type":"integer"}},"additionalProperties":false},"annotations":{"title":"List audit log entries","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"05ddd4a8f50fb909554ef54f11c212baefc23402fd1bdfb6566bf5e48f192d78","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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 an event's prompt text, reason, model or names. Read-only.\nWhen to use: To investigate what PromptGuard caught recently, to check whether a project is seeing attacks, or to find the event and rule behind a Suppression the User asks for on a project they name (by project_name).","inputSchema":{"type":"object","properties":{"decision":{"anyOf":[{"items":{"enum":["allow","block","redact","flag","override"],"type":"string"},"type":"array"},{"type":"null"}],"default":null,"description":"Only events with one of these decisions"},"threat_type":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only events of this threat type, e.g. prompt_injection or pii_leak"},"project_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only events in this project"},"project_name":{"anyOf":[{"maxLength":255,"minLength":1,"type":"string"},{"type":"null"}],"default":null,"description":"Only events in the project with this name, as the User typed it (case ignored). Not with project_id."},"since":{"anyOf":[{"format":"date-time","type":"string"},{"type":"null"}],"default":null,"description":"Only events at or after this time (ISO 8601; UTC if no zone)"},"limit":{"default":20,"description":"How many events to return","maximum":50,"minimum":1,"type":"integer"}},"additionalProperties":false},"annotations":{"title":"List security events","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ba401a2cce74e16c6a9f21605d999f787b34eef87030e698e7763a3e0e03051c","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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, or to audit a project's coverage.","inputSchema":{"type":"object","properties":{"include_inactive":{"default":false,"description":"Include policies that are switched off","type":"boolean"}},"additionalProperties":false},"annotations":{"title":"List policies","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"65797d12253de937f5058a1183faa25d5df0a36db8b6709d30f32c604c7d4801","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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 check how a project is set up, or which projects fail open.","inputSchema":{"type":"object","properties":{},"additionalProperties":false},"annotations":{"title":"List projects and their configuration","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"4e3b0668b86f2f15d5255401e8af0a9e9232d67f8ca6d1eb62257e484953d553","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{"category":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only tests in this category, e.g. prompt_injection or jailbreak"}},"additionalProperties":false},"annotations":{"title":"List red-team tests","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ff81c265baab524a0b95413d9828086a31c72e3ec9e9b949ea87f754c8ba066f","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{"project_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Only deliveries of this project"},"limit":{"default":20,"description":"How many deliveries to return","maximum":50,"minimum":1,"type":"integer"}},"additionalProperties":false},"annotations":{"title":"List webhook deliveries","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"aaca6d238039304854e0bf58a2e809358c10cde68ae03c2a58fa52dc1d2571d1","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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 5 minutes. From any other MCP client, the User's approval of this call is the confirmation: the Suppression is made at once, recorded in the audit log as this client's action, and can be deleted in the project's settings, under Suppressions.\nAlready suppressed: if the rule is already suppressed on the project until sooner, this extends that Suppression (the result's extended_from says until when it ran before); if it already lasts as long, the call is refused, as there is nothing to change.\nExpiry: 30 days unless the User asks for another, at most 90.\nWhen to use: The User asks to silence a rule that keeps flagging something they say is safe.","inputSchema":{"type":"object","properties":{"project_id":{"description":"The project's id","maxLength":64,"minLength":1,"type":"string"},"detector":{"description":"The detector, as a finding's rule.detector names it","maxLength":100,"minLength":1,"pattern":"^[A-Za-z0-9_.:-]+$","type":"string"},"rule_id":{"description":"The rule of that detector, as a finding's rule.id names it","maxLength":200,"minLength":1,"pattern":"^[A-Za-z0-9_.:/-]+$","type":"string"},"expires_in_days":{"default":30,"description":"How many days until it stops applying","maximum":90,"minimum":1,"type":"integer"}},"required":["project_id","detector","rule_id"],"additionalProperties":false},"annotations":{"title":"Suppress a rule on a project","readOnlyHint":false,"destructiveHint":true,"idempotentHint":false,"openWorldHint":false},"definitionHash":"c922cbb23f4d5342aee91f9920a9046296de2073a3e884c748d7946891f2a8bd","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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 Project redacts emails, phone numbers, SSNs, payment cards, bank and national identifiers, IP addresses and API keys. Pass `pii_types` to redact only the types you name. An email at a domain reserved for documentation and testing (example.com, .test, .invalid, localhost) is never redacted, since it cannot be a person's address: it comes back in `skipped` with the reason `reserved_domain`, so test with a real-looking domain.\nWhen to use: Before including user data in LLM prompts, when processing customer messages, or when building RAG pipelines that ingest documents containing personal information.","inputSchema":{"type":"object","properties":{"text":{"description":"The text content to redact PII from","type":"string"},"pii_types":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"default":null,"description":"PII types to redact, the REST API's vocabulary: detector entity names ('email', 'ssn', 'credit_card', 'phone_us'), the family aliases 'phone', 'ip_address' and 'passport', and 'api_key'. Omit to redact what the Project's policy redacts. An unrecognized name is refused with the code 'unknown_pii_type' rather than ignored."}},"required":["text"],"additionalProperties":false},"annotations":{"title":"Redact PII","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"b3a3638ee845df414d5e49711563ac3a36eadfe6a44c87a29dd2df3360850be9","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{"code":{"description":"The code content to analyze for LLM SDK usage","type":"string"}},"required":["code"],"additionalProperties":false},"annotations":{"title":"Find LLM SDK calls in code","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"56618988aeefce20fda77f33bf349b9f6f43d9243d619b3b561fe662f4ecd5cd","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{"text":{"description":"The text content to scan for security threats","type":"string"},"content_type":{"default":"prompt","description":"Whether the text is a prompt sent to a model or a model's response","enum":["prompt","response"],"type":"string"}},"required":["text"],"additionalProperties":false},"annotations":{"title":"Scan text for threats","readOnlyHint":true,"destructiveHint":false,"openWorldHint":false},"definitionHash":"ade5448139e0ba3578721c666eb631690a4bad6762b2b57a06ea8386dc5f4891","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"},{"serverName":"co.promptguard/security","endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","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.","inputSchema":{"type":"object","properties":{},"additionalProperties":false},"annotations":{"title":"PromptGuard status","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"3dc817e5aaed76d03ddfb607707fe4f33671901bfe1b3a9dd5c6f2d3c446e21c","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-17T07:46:02.700Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"7451a03da3c02bd5bd8a7a3258d17c74d7082ef7a5eb3b0da78d5c1cdefcfcba","protocol":"streamable-http","status":"indexed","toolCount":13,"observedAt":"2026-11-17T07:46:02.700Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"co.promptguard/security":{"url":"https://api.promptguard.co/mcp"}}},"Cursor":{"mcpServers":{"co.promptguard/security":{"url":"https://api.promptguard.co/mcp"}}},"VS Code":{"servers":{"co.promptguard/security":{"type":"http","url":"https://api.promptguard.co/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://api.promptguard.co/mcp"},{"protocol":"mcp","package":"@promptguard/mcp-server","registryType":"npm","version":"1.2.5"},{"protocol":"mcp","package":"ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5","registryType":"oci","version":null}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:co.promptguard%2Fsecurity","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/co.promptguard%2Fsecurity","name":"co.promptguard/security","description":"Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://api.promptguard.co/mcp"},{"protocol":"mcp","package":"@promptguard/mcp-server","registryType":"npm","version":"1.2.5"},{"protocol":"mcp","package":"ghcr.io/promptguardhq/promptguard-mcp-server:1.2.5","registryType":"oci","version":null}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://promptguard.co","repositoryUrl":"https://github.com/promptguardhq/promptguard","version":"1.2.5"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"co.promptguard/security","status":"online","lastCheckedAt":"2026-11-20T05:15:52.451Z","lastSuccessfulCheck":"2026-11-20T05:15:52.451Z","latencyMs":35,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T05:15:52.451Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T05:15:52.451Z"},"security":null,"timestamps":{"createdAt":"2026-11-13T03:36:26.827Z","updatedAt":"2026-11-13T03:36:26.827Z","observedAt":"2026-11-20T05:15:52.451Z"},"compatibility":{"serverVersion":"1.2.5","protocolVersions":[{"protocol":"mcp","version":null}]}}}}