// SCAN REPORT

Cortex

31 tools. 14 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

14 can modify or destroy data

17 read-only

31 tools total

Community server · catalogue entry verified 30/06/2026

How to control Cortex ↓

TOOL MAP

What Cortex exposes to your agents

Read (17) Write / Execute (11) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Cortex tools

Destructive · High cortex_cleanup_jobs This tool performs irreversible deletion of job records at scale. Destructive · High cortex_delete_job This tool permanently deletes analysis job records, which cannot be undone. Destructive · High cortex_disable_analyzer The tool explicitly removes an enabled analyzer from the organization, which is a destructive action. Execute · High cortex_run_analyzer This tool executes an external analyzer on user-supplied data.

14 of Cortex's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Cortex

PolicyLayer is an MCP gateway — it sits between your AI agents and Cortex, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cortex_cleanup_jobs": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "cortex_create_organization": {
    "limits": [
      {
        "counter": "cortex_create_organization_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cortex_get_analyzer": {
    "limits": [
      {
        "counter": "cortex_get_analyzer_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Cortex — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CORTEX →

Instant setup, no code required.

FULL CATALOGUE

All 31 Cortex tools

DESTRUCTIVE 3 tools

Destructive cortex_cleanup_jobs Delete multiple jobs by status or age. Useful for cleaning up failed or old jobs. Destructive cortex_delete_job Delete a specific analysis job by ID. DESTRUCTIVE: requires confirm=true. Destructive cortex_disable_analyzer Disable (remove) an enabled analyzer from the current organization. DESTRUCTIVE: requires confirm=true.

EXECUTE 5 tools

Execute cortex_analyze_observable Run applicable analyzers against an observable and collect aggregated results with taxonomy summary. Can auto- Execute cortex_run_analyzer Submit an observable to a specific analyzer for analysis Execute cortex_run_analyzer_by_name Run an analyzer by name instead of ID (convenience wrapper) Execute cortex_run_analyzer_file Submit a file to a specific analyzer for analysis. Provide a file path or base64-encoded content. Execute cortex_run_responder Execute a responder action against a TheHive entity (case, task, artifact, alert). DESTRUCTIVE: responders per

WRITE 6 tools

Write cortex_create_organization Create a new organization in Cortex (requires superadmin API key) Write cortex_create_user Create a new user in an organization (requires superadmin API key) Write cortex_disable_responder Disable (remove) an enabled responder from the current organization Write cortex_enable_analyzer Enable an analyzer definition in the current organization. Provide configuration values for any required field Write cortex_enable_responder Enable a responder definition in the current organization. Provide configuration values for any required field Write cortex_update_organization Update an organization

READ 17 tools

Read cortex_get_analyzer Get details about a specific analyzer by ID Read cortex_get_job Get the status and details of an analysis job Read cortex_get_job_artifacts Get artifacts (extracted observables/IOCs) from a completed analysis job Read cortex_get_job_report Get the full report of a completed analysis job Read cortex_get_organization Get details about a specific organization (requires superadmin API key) Read cortex_get_status Get Cortex instance health status, version info, and configuration Read cortex_get_user Get details about a specific user (requires superadmin API key) Read cortex_get_user_key Get the current API key for a user. Requires superadmin API key. Read cortex_list_analyzer_definitions List all available analyzer definitions (installed but not necessarily enabled). Filter by data type or find a Read cortex_list_analyzers List all enabled analyzers, optionally filtered by data type Read cortex_list_jobs List recent analysis jobs with optional filters Read cortex_list_organizations List all organizations (requires superadmin API key via CORTEX_SUPERADMIN_KEY) Read cortex_list_responder_definitions List all available responder definitions (installed but not necessarily enabled). Filter by data type or find Read cortex_list_responders List all enabled responders, optionally filtered by data type Read cortex_list_users List all users across organizations (requires superadmin API key via CORTEX_SUPERADMIN_KEY) Read cortex_renew_user_key Generate a new API key for a user (invalidates the previous key). Requires superadmin API key. Read cortex_wait_and_get_report Wait for a job to complete and return the full report (with polling timeout)

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Cortex

Can an AI agent delete data through the Cortex MCP server? +

Yes. The Cortex server exposes 3 destructive tools including cortex_cleanup_jobs, cortex_delete_job, cortex_disable_analyzer. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Cortex? +

The Cortex server has 6 write tools including cortex_create_organization, cortex_create_user, cortex_disable_responder. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Cortex.

How many tools does the Cortex MCP server expose? +

31 tools across 4 categories: Destructive, Execute, Read, Write. 17 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Cortex? +

Register the Cortex MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Cortex tool call.

Deterministic rules across all 31 Cortex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CORTEX →

Instant setup, no code required.

31 Cortex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.