# Petra Security (oci · ghcr.io/wyre-ai/petra-mcp) Read-only Petra Security MCP: M365 compromise incidents, failed attacks, posture, tenants, usage. - Trust score: 33/100 (low) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-05 ## Components - oci · `ghcr.io/wyre-ai/petra-mcp`: 33/100 (this document), [markdown](https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp.md), [page](https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp) ## Channel facts - Registry: `oci` - Package: `ghcr.io/wyre-ai/petra-mcp` - Version: `v1.0.0` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-05. - **Supply Chain Security**: 0/100 - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package. - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read. - Install-script risk not yet assessed. - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read. - **Provenance & Transparency**: 6/100 - Repository check failed: the declared repository URL returned HTTP 404. - Provenance check failed: no build-provenance attestation is published. - License check failed: the license (NOASSERTION) isn't a recognized OSI-approved license. - Actively maintained (last published 15 days ago). - Security-disclosure policy not yet verified: we couldn't inspect the source repository. - **Schema Quality & AI Usability**: 70/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 1300 tokens (~185/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 7/100 - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. **Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm. ## Install ### How do I install the Petra Security MCP server? Petra Security runs locally as a container image, launched with docker run --rm -i -e PETRA_API_KEY -e MCP_TRANSPORT -e AUTH_MODE -e LOG_LEVEL ghcr.io/wyre-ai/petra-mcp:v1.0.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add wyre-ai-petra-mcp -- docker run --rm -i -e PETRA_API_KEY -e MCP_TRANSPORT -e AUTH_MODE -e LOG_LEVEL ghcr.io/wyre-ai/petra-mcp:v1.0.0 ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### Cursor ```json { "mcpServers": { "wyre-ai-petra-mcp": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0" ] } } } ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### VS Code ```json { "servers": { "wyre-ai-petra-mcp": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0" ] } } } ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### Codex ```bash codex mcp add wyre-ai-petra-mcp -- docker run --rm -i -e PETRA_API_KEY -e MCP_TRANSPORT -e AUTH_MODE -e LOG_LEVEL ghcr.io/wyre-ai/petra-mcp:v1.0.0 ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "wyre-ai-petra-mcp": { "type": "local", "command": [ "docker", "run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0" ], "enabled": true } } } ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### Hermes ```yaml mcp_servers: wyre-ai-petra-mcp: command: "docker" args: ["run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0"] ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### Netclaw ```json { "McpServers": { "wyre-ai-petra-mcp": { "Transport": "stdio", "Command": "docker", "Arguments": [ "run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0" ] } } } ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ### Other ```json { "mcpServers": { "wyre-ai-petra-mcp": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "PETRA_API_KEY", "-e", "MCP_TRANSPORT", "-e", "AUTH_MODE", "-e", "LOG_LEVEL", "ghcr.io/wyre-ai/petra-mcp:v1.0.0" ] } } } ``` This image reads PETRA_API_KEY, MCP_TRANSPORT, AUTH_MODE and LOG_LEVEL. Set them in your client's env block for this server; docker run -e passes each one through to the container. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-11-05 (score 33, +1) No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-11-03 (score 32) First indexed and scored. ## MCP tools (7) ### `petra_list_tenants` (~118 tokens) List every client tenant (Microsoft 365 customer) in the Petra organization, alphabetically, with its Petra tenant ID, Microsoft tenant ID, onboarding date and paused flag. Start here to find the tenantId other petra_* tools take. Removed tenants are excluded; paused tenants are included unless includePaused is false. Input parameters: - `includePaused` (boolean): Include tenants whose ingestion is paused. Defaults to true. - `nameContains` (string): Case-insensitive substring match on the tenant name (filtered locally; Petra has no search parameter). ### `petra_get_usage` (~149 tokens) Get the whole-organization Petra billing snapshot in one call: for every tenant, the service (Monitoring or Autopsy), billableStatus (Trial, Active, NFR, Deleted), totalLicensedUsers, billableUsersThisMonth, proratingPercentageThisMonth and firstBillableDate, plus totals across the returned tenants. Use for invoice reconciliation against the PSA. Input parameters: - `asOf` (string): Usage as of this date (YYYY-MM-DD). Defaults to today. - `billableStatus` (string): Only return tenants with this billable status (filtered locally). - `includePaused` (boolean): Include paused tenants. Defaults to true. Set false so paused tenants do not inflate counts. ### `petra_list_billable_users` (~156 tokens) List the individual billable users for ONE tenant (users with an assigned Microsoft license that are not deleted), with display name, UPN, mail, enabled flag and license SKU IDs, plus totalBillableUsers and projectedBillableUnitsThisMonth. This is the user-level detail behind petra_get_usage. A Microsoft tenant ID is resolved to the Petra tenant ID automatically. Input parameters: - `enabledOnly` (boolean): Only return users whose account is enabled (filtered locally). Totals still reflect Petra’s count. - `tenantId` (string, required): Petra tenant ID (from petra_list_tenants, or the app.petrasecurity.com/tenant/ URL) or the Microsoft tenant ID; Petra resolves either. ### `petra_list_incidents` (~303 tokens) List Microsoft 365 identity-compromise incidents Petra detected (account takeovers, BEC), newest first: compromised user, occurred/created time, remediation status, whether the attacker is still live, dwell time, and the phishing email that led to it. Omit tenantId to search every tenant in the organization. Petra only alerts on real compromises. Input parameters: - `includePhishingEmail` (boolean): Include the phishingEmail details block. Defaults to true; set false for a compact list. - `limit` (integer): Maximum incidents Petra returns (1-500, default 100). Local filters below apply after this limit. - `liveOnly` (boolean): Only incidents where the attacker is still live (isLive=true). - `remediationStatus` (string): Only incidents with this remediationStatus (e.g. REMEDIATED, REMEDIATED_PRIOR_TO_ONBOARDING). Filtered locally, case-insensitive. - `startDate` (string): Only incidents created on or after this ISO 8601 date or date-time (e.g. 2026-03-01). - `tenantId` (string): Limit to one tenant. Petra tenant ID (from petra_list_tenants, or the app.petrasecurity.com/tenant/ URL) or the Microsoft tenant ID; Petra resolves either. - `userPrincipalName` (string): Only incidents for this user (UPN or mail, case-insensitive). Filtered locally. ### `petra_get_incident` (~152 tokens) Get one Petra incident by its ID, with full user and phishing-email detail. Petra has no single-incident route, so this searches the newest 500 incidents (pass tenantId to reach older ones). Input parameters: - `incidentId` (string, required): Incident ID (UUID) from petra_list_incidents or the Petra incident URL. - `startDate` (string): Only search incidents created on or after this ISO 8601 date. - `tenantId` (string): Tenant the incident belongs to, to widen the search window. Petra tenant ID (from petra_list_tenants, or the app.petrasecurity.com/tenant/ URL) or the Microsoft tenant ID; Petra resolves either. ### `petra_get_failed_attacks` (~189 tokens) Get the BLOCKED (failed) attack summary for one tenant: total count, counts by origin country, a daily breakdown by attack type (e.g. PASSWORD_SPRAY, LEGACY_AUTH), and the most-targeted users with the countries their attackers came from. Defaults to the last 30 days. Petra rate-limits this route heavily, so results are cached for 5 minutes. Input parameters: - `endDate` (string): End of the window, ISO 8601 date or date-time. Defaults to now. - `startDate` (string): Start of the window, ISO 8601 date or date-time. Defaults to 30 days before endDate. - `tenantId` (string, required): Petra tenant ID (from petra_list_tenants, or the app.petrasecurity.com/tenant/ URL) or the Microsoft tenant ID; Petra resolves either. ### `petra_list_posture_reports` (~233 tokens) Get completed Microsoft 365 security posture reports: score and grade (with previous score/grade on follow-ups), control rollup (secure, fixed, open, drifted), the Global Administrators review (count, MFA strength, password age), top risks, and every check with its status, severity, current state and suggested fix. By default returns the latest report per tenant. Input parameters: - `includeChecks` (boolean): Include the per-control checks array. Defaults to true; set false for a compact score/top-risks view. - `latestOnly` (boolean): Only the most recent completed report per tenant (default true). Set false for history, newest first. - `limit` (integer): Maximum reports (1-500, default 100). - `startDate` (string): Only reports completed on or after this ISO 8601 date or date-time. - `tenantId` (string): Limit to one tenant. Petra tenant ID (from petra_list_tenants, or the app.petrasecurity.com/tenant/ URL) or the Microsoft tenant ID; Petra resolves either. ## Diagnostics Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp#diagnostics ## Score history - 2026-11-05: 33 - 2026-11-04: 32 - 2026-11-03: 32 ## Common questions ### What is the Petra Security MCP server? Petra Security is an MCP server listed in the public MCP registry as io.github.WYRE-AI/petra-mcp. Read-only Petra Security MCP: M365 compromise incidents, failed attacks, posture, tenants, usage. This page covers its container image (ghcr.io/wyre-ai/petra-mcp). ### Is the Petra Security MCP server safe to use? Petra Security scores 33 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the Petra Security MCP server expose? Petra Security exposes 7 tools: petra_list_tenants, petra_get_usage, petra_list_billable_users, petra_list_incidents, petra_get_incident, and 2 more. Their descriptions and schemas cost roughly 1,300 tokens of context every time the server is loaded. ### Is the Petra Security MCP server still maintained? Petra Security is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ### What licence is the Petra Security MCP server under? Petra Security declares the NOASSERTION licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls. ## Links - GitHub Container Registry: https://ghcr.io/wyre-ai/petra-mcp - Changelog RSS feed: https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp.json - HTML version of this page: https://verifymcp.io/servers/wyre-ai-petra-mcp/ghcr-io-wyre-ai-petra-mcp