// SCAN REPORT

Cortex Hub

25 tools. 10 can modify or destroy data without limits.

10 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

10 can modify or destroy data

15 read-only

25 tools total

Community server · catalogue entry verified 11/06/2026

How to control Cortex Hub ↓

TOOL MAP

What Cortex Hub exposes to your agents

Read (15) Write / Execute (10) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Cortex Hub tools

Execute · Medium cortex_code_reindex This tool executes an external indexing operation (re-index job) on a specified project. Execute · High cortex_cypher This tool executes database queries in Cypher language against an underlying knowledge graph. Write · Low cortex_session_start This tool creates a new session (a write/create operation) and associates agent identity metadata with it. Write · Medium cortex_task_create This tool creates new task records in the system, which is a reversible write operation.

10 of Cortex Hub's 25 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 Hub

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

Rate limit write operations

{
  "cortex_session_start": {
    "limits": [
      {
        "counter": "cortex_session_start_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cortex_changes": {
    "limits": [
      {
        "counter": "cortex_changes_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 Hub — 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 HUB →

Free to start. No card required.

FULL CATALOGUE

All 25 Cortex Hub tools

EXECUTE 2 tools

Execute cortex_code_reindex Trigger re-indexing of a project after code changes. Looks up the project by repo URL and starts a GitNexus re Execute cortex_cypher Run Cypher queries directly against the GitNexus knowledge graph. Supports MATCH, RETURN, WHERE, ORDER BY for

WRITE 8 tools

Write cortex_session_start Start a new execution session with optional agent identity metadata. Write cortex_knowledge_store Store a knowledge document in the Cortex knowledge base. Auto-chunks and embeds the content for semantic searc Write cortex_memory_store Store a memory for an AI agent. Memories persist across sessions and can be recalled by semantic search. Use p Write cortex_session_end Close a session with a summary of work done. Reports session duration and compliance. Write cortex_task_accept Accept an assigned task, signaling that work will begin. Updates task status to accepted. Write cortex_task_create Create a task and optionally assign it to another agent. Use for delegating work, tracking sub-tasks, or creat Write cortex_task_submit_strategy Submit a task execution strategy for user review. The Lead Agent calls this after analyzing a task to propose Write cortex_task_update Update the status of a task. Use to transition tasks through their lifecycle: in_progress, review, completed,

READ 15 tools

Read cortex_changes Check for recent code changes pushed by other agents/team members. Returns unseen commits and affected files. Read cortex_code_context Get a 360° view of a code symbol: its methods, callers, callees, and related execution flows. Essential for ex Read cortex_code_impact Analyze the blast radius of changing a specific symbol (function, class, file) to verify downstream impact bef Read cortex_code_read Read raw source code from an indexed repository. Returns full file content or a line range. Use after cortex_c Read cortex_code_search Query the codebase for architecture concepts, execution flows, and file matches using GitNexus hybrid vector/A Read cortex_detect_changes Detect uncommitted changes and analyze their risk level across the indexed codebase. Shows changed symbols, af Read cortex_health Check health status of all Cortex Hub backend services Read cortex_knowledge_search Search the platform knowledge base by semantic similarity. Returns relevant document snippets with metadata, t Read cortex_list_repos List all indexed repositories with project ID mapping. Use this to find which projectId to pass to code_search Read cortex_memory_search Search agent memories by semantic similarity. Use projectId + branch to search branch-specific knowledge with Read cortex_quality_report Report the results of a Quality Gate check (e.g. Forgewright Phase/Gate checks, test outputs, lint records) Read cortex_task_list List tasks with optional filters for project, status, and assignee. Use to get an overview of task state. Read cortex_task_pickup Retrieve tasks assigned to you. Automatically checks both your agentId and API key name. Read cortex_task_status Get the detailed status of a specific task including its logs and history. Read cortex_tool_stats View Cortex MCP tool usage analytics: success rates, latency, token estimates, and trends. Use to measure Cort

EXPLORE

Related servers

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

FAQ

Questions about Cortex Hub

How do I prevent bulk modifications through Cortex Hub? +

The Cortex Hub server has 8 write tools including cortex_session_start, cortex_knowledge_store, cortex_memory_store. 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 Hub.

How many tools does the Cortex Hub MCP server expose? +

25 tools across 3 categories: Execute, Read, Write. 15 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Cortex Hub? +

Register the Cortex Hub 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 Hub tool call.

Deterministic rules across all 25 Cortex Hub tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CORTEX HUB →

Free to start. No card required.

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