Skip to content

Systemores AI Agent & MCP Security Auditor

io.github.bobcar0/systemores-pluginbobcar0streamable-httpv1.2.1Scanned

AI agent security, MCP 2026 schema & graph audits, <250ms guardrails, and compliance dossiers

12 tools: 11 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 11 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 6
  • Can send data out · 0
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

11 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Systemores AI Agent & MCP Security Auditor can do

The Systemores AI Agent & MCP Security Auditor is published by the GitHub account bobcar0. It has 12 tools. It can create or change data (11 tools: systemores_stress_test_agent, systemores_evaluate_drift, systemores_assess_bias, systemores_measure_drag and 7 more), but cannot delete data. 1 tool only reads.

6 tools bring in text other people can write (systemores_stress_test_agent, systemores_evaluate_drift, systemores_assess_bias and 3 more).

The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 1.2.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

12 tools

Changes things 11Claude Code: ask
  • systemores_assess_biasVerifies the agent's compliance with fair-lending, fair-housing, employment non-discrimination (EEOC/SIOP/ECOA), child-directed safety (COPPA), or EU AI Act (EU 2024/1689) standard…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Verifies the agent's compliance with fair-lending, fair-housing, employment non-discrimination (EEOC/SIOP/ECOA), child-directed safety (COPPA), or EU AI Act (EU 2024/1689) standards.

    Annotations the server declares

    • title: Assess Regulatory & Demographic Bias
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • systemores_audit_agent_graphStatically scans multi-agent execution topologies (DAGs/meshes) using DFS algorithms to detect cyclic delegation loops and privilege escalation paths from public untrusted sub-agen…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Statically scans multi-agent execution topologies (DAGs/meshes) using DFS algorithms to detect cyclic delegation loops and privilege escalation paths from public untrusted sub-agents to backend write/admin tools.

    Annotations the server declares

    • title: Audit Multi-Agent Execution Topology
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • systemores_audit_tool_integrityAudits the structural integrity, naming conventions, schema completeness, safety annotations, and injection surface of an AI agent's exposed tool definitions.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Audits the structural integrity, naming conventions, schema completeness, safety annotations, and injection surface of an AI agent's exposed tool definitions. Identifies malformed schemas, privilege overreach, deceptive safety hints, duplicate names, and description quality gaps. Operates entirely offline — no external API calls required.

    Annotations the server declares

    • title: Audit MCP Tool Definitions Integrity
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • systemores_audit_turn_livePerforms real-time (~250ms) operational and behavioral turn auditing using Systemores System One.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Performs real-time (~250ms) operational and behavioral turn auditing using Systemores System One. Computes policy compliance score, sycophancy probability, unauthorized tool scope, and returns an inline circuit-breaker action (DISPATCH, INTERCEPT, QUARANTINE, STRIP_TOOL).

    Annotations the server declares

    • title: Live Turn Audit (Systemores System One)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • systemores_evaluate_driftSimulates multiple conversational turns to evaluate agent output consistency and behavioral drift over extended interactions.Reads text others write1 finding

    Why it is in this group

    • The name "systemores_evaluate_drift" says "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "systemores_evaluate_drift" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "systemores_evaluate_drift" says "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Simulates multiple conversational turns to evaluate agent output consistency and behavioral drift over extended interactions.

    Annotations the server declares

    • title: Evaluate Multi-Turn Behavioral Drift
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • systemores_export_dossierAggregates findings from graph audits, synthetic cohort simulations, chaos tests, trace analytics, and optional transient systemPrompt/tool/graph/OTel evidence (zero-retention) int…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Aggregates findings from graph audits, synthetic cohort simulations, chaos tests, trace analytics, and optional transient systemPrompt/tool/graph/OTel evidence (zero-retention) into dynamically scored, localized (en, es, de, fr, pt, ja, zh) signed compliance dossiers with verifiable certificate links and live SVG trust badges for EU AI Act (EU 2024/1689), NIST AI RMF 1.0, EEOC/ECOA, and SOC 2 AI Addendums.

    Annotations the server declares

    • title: Export Regulatory Compliance Dossier
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • systemores_generate_cohortGenerates statistical cohorts of synthetic user personas (localized across en, es, de, fr, pt, ja, zh) across enterprise operational domains with IPIP-NEO-120 30-facet psychometric…Reads text others write1 finding

    Why it is in this group

    • The name "systemores_generate_cohort" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "systemores_generate_cohort" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "systemores_generate_cohort" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generates statistical cohorts of synthetic user personas (localized across en, es, de, fr, pt, ja, zh) across enterprise operational domains with IPIP-NEO-120 30-facet psychometric profiles, demographic diversity, and prompt injection payloads.

    Annotations the server declares

    • title: Generate Synthetic IPIP-NEO-120 Persona Cohort
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • systemores_inject_environment_faultConfigures dynamic chaos injection policies for tools, mock APIs, and databases during simulations (HTTP 429 rate limits, 500 errors, timeouts, 401 unauthorized, malformed JSON).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Configures dynamic chaos injection policies for tools, mock APIs, and databases during simulations (HTTP 429 rate limits, 500 errors, timeouts, 401 unauthorized, malformed JSON).

    Annotations the server declares

    • title: Generate Chaos Fault Injection Policy
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • systemores_measure_dragMeasures operational latency, response length, and execution drag parameters to analyze cognitive throughput stability within the Behavioral OS ecosystem.1 finding

    Why it is in this group

    • The name "systemores_measure_drag" says "drag": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "systemores_measure_drag" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "systemores_measure_drag" says "drag": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Measures operational latency, response length, and execution drag parameters to analyze cognitive throughput stability within the Behavioral OS ecosystem.

    Annotations the server declares

    • title: Measure Cognitive Throughput Drag
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • systemores_stress_test_agentExposes the target agent persona to a battery of adversarial prompts (Presses) and evaluates behavioral stability using Murray's Needs-Press diagnostic model.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Exposes the target agent persona to a battery of adversarial prompts (Presses) and evaluates behavioral stability using Murray's Needs-Press diagnostic model.

    Annotations the server declares

    • title: Stress Test Agent Persona (Murray's Needs-Press)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • systemores_tool_integrityEvaluates whether the agent's system prompt establishes the behavioral conditions for safe, reliable tool use — auditing tool selection discipline, argument construction fidelity, …Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "systemores_tool_integrity" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates whether the agent's system prompt establishes the behavioral conditions for safe, reliable tool use — auditing tool selection discipline, argument construction fidelity, and failure resilience when tool returns are ambiguous or erroneous.

    Annotations the server declares

    • title: Evaluate System Prompt Tool Discipline
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • systemores_analyze_trace_telemetryIngests standard OpenTelemetry (OTel) trace JSON payloads to detect financial token cost burn traps (> $2.50 threshold), runtime loop deadlocks between sub-agents, and cognitive la…No findings

    Why it is in this group

    • The name "systemores_analyze_trace_telemetry" says "analyze": a word for reading.
    Description, as the server wrote it
    Ingests standard OpenTelemetry (OTel) trace JSON payloads to detect financial token cost burn traps (> $2.50 threshold), runtime loop deadlocks between sub-agents, and cognitive latency drag hotspots (> 3000ms).

    Annotations the server declares

    • title: Analyze OpenTelemetry Agent Trace Spans
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:21 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://audit.systemores.com/api/mcp: tools/list returned 12 tools to an anonymous client, including systemores_stress_test_agent (write), systemores_evaluate_drift (write), systemores_assess_bias (write), systemores_measure_drag (write), systemores_tool_integrity (write) and 6 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 warn
  • The server marks "systemores_evaluate_drift" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "systemores_evaluate_drift" says "evaluate": a word for a change.

    What this check looks for
  • The server marks "systemores_measure_drag" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "systemores_measure_drag" says "drag": a word for a change.

    What this check looks for
  • The server marks "systemores_tool_integrity" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The server marks "systemores_generate_cohort" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "systemores_generate_cohort" says "generate": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. Tools3 changed.~3 changedView diff
  3. Tools1 changed.~1 changedView diff

Install

Pinned to version 1.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http systemores-plugin https://audit.systemores.com/api/mcp
claude mcp add --transport http systemores-plugin https://audit.systemores.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__systemores-plugin__systemores_analyze_trace_telemetry"
    ],
    "ask": [
      "mcp__systemores-plugin__systemores_stress_test_agent",
      "mcp__systemores-plugin__systemores_evaluate_drift",
      "mcp__systemores-plugin__systemores_assess_bias",
      "mcp__systemores-plugin__systemores_measure_drag",
      "mcp__systemores-plugin__systemores_tool_integrity",
      "mcp__systemores-plugin__systemores_audit_tool_integrity",
      "mcp__systemores-plugin__systemores_audit_agent_graph",
      "mcp__systemores-plugin__systemores_generate_cohort",
      "mcp__systemores-plugin__systemores_inject_environment_fault",
      "mcp__systemores-plugin__systemores_export_dossier",
      "mcp__systemores-plugin__systemores_audit_turn_live"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as systemores-plugin. Review it before you use it.

Capability tags behind 6 rules
  • mcp__systemores-plugin__systemores_stress_test_agent untrusted-input
  • mcp__systemores-plugin__systemores_evaluate_drift untrusted-input
  • mcp__systemores-plugin__systemores_assess_bias untrusted-input
  • mcp__systemores-plugin__systemores_tool_integrity untrusted-input
  • mcp__systemores-plugin__systemores_generate_cohort untrusted-input
  • mcp__systemores-plugin__systemores_audit_turn_live untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.bobcar0/systemores-plugin/verify?hash=02b3472ed5d9179bb6399fd3b2f21954415d4a3080783016eeae2830f180caa6" | jq -e '.changed == false'

Pinned hash 02b3472ed5d9, from Nov 21, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.bobcar0/systemores-plugin/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.bobcar0/systemores-plugin
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.bobcar0/systemores-plugin.svg)](https://radar.anlyon.com/servers/io.github.bobcar0/systemores-plugin)

Source: MCP Registry · repository. Synced Nov 21, 2026, 20:17 UTC.

Systemores AI Agent & MCP Security Auditor: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Systemores AI Agent & MCP Security Auditor safe?

No scan can promise that. What its definitions show: 12 tools, 11 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Systemores AI Agent & MCP Security Auditor delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Systemores AI Agent & MCP Security Auditor do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Systemores AI Agent & MCP Security Auditor have?

12 tools: 11 write, 1 read. systemores_stress_test_agent, systemores_evaluate_drift, systemores_assess_bias, systemores_measure_drag, systemores_tool_integrity, systemores_audit_tool_integrity, systemores_audit_agent_graph, systemores_generate_cohort and 4 more.

Does the Systemores AI Agent & MCP Security Auditor need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Systemores AI Agent & MCP Security Auditor send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Systemores AI Agent & MCP Security Auditor changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.