// SCAN REPORT

AgentCortex MCP

14 tools. 7 can modify or destroy data without limits.

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

Last updated: 28 Jun 2026

7 can modify or destroy data

7 read-only

14 tools total

Community server · catalogue entry verified 28/06/2026

How to control AgentCortex MCP ↓

TOOL MAP

What AgentCortex MCP exposes to your agents

Read (7) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous AgentCortex MCP tools

Write · Low create_project This tool creates new data (a project) in a reversible manner. Write · Low create_task The tool creates new task records, which is a reversible write operation. Write · Medium set_current_project This tool modifies persistent application state (the current project selection) that persists across operations and influences the behavior of other tools. Write · Medium update_memory_importance This tool modifies existing memory records by changing their importance/priority levels.

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

POLICY

How to control AgentCortex MCP

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

Rate limit write operations

{
  "break_down_task": {
    "limits": [
      {
        "counter": "break_down_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_current_project": {
    "limits": [
      {
        "counter": "get_current_project_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 AgentCortex MCP — 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 AGENTCORTEX →

Instant setup, no code required.

FULL CATALOGUE

All 14 AgentCortex MCP tools

WRITE 7 tools

Write break_down_task Break down a complex task into smaller, manageable subtasks. Helps with project planning and execution. Write create_project Create a new project to organize memories and tasks. Projects help separate different work contexts and make i Write create_task Create a new task within the current project. Tasks help organize work and track progress on specific objectiv Write set_current_project Switch the active project context. All memory and task operations will use this project until changed. Write store_memory Store important information in persistent memory for later retrieval. Use this to remember key facts, decision Write update_memory_importance Update the importance level of an existing memory. Use this to prioritize critical information or de-prioritiz Write update_task_status Update the status of an existing task. Use this to track progress and mark tasks as completed.

READ 7 tools

Read get_current_project Get information about the currently active project, including stats on memories and tasks. Read get_memories Retrieve memories with optional filtering by type and date range. Returns memories in reverse chronological or Read get_project_context Get comprehensive project overview including recent memories, active tasks, and project statistics. Read list_projects List all available projects with their basic information and statistics. Read list_tasks List tasks in the current project with optional filtering by status, priority, or assignee. Read search_memory Search through stored memories using semantic search. Finds memories related to your query even if they don\ Read suggest_next_task Get AI-powered suggestions for the next task to work on based on current project context and priorities.

FAQ

Questions about AgentCortex MCP

How do I prevent bulk modifications through AgentCortex MCP? +

The AgentCortex MCP server has 7 write tools including break_down_task, create_project, create_task. 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 AgentCortex MCP.

How many tools does the AgentCortex MCP server expose? +

14 tools across 2 categories: Read, Write. 7 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on AgentCortex MCP? +

Register the AgentCortex 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 AgentCortex MCP tool call.

Deterministic rules across all 14 AgentCortex MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENTCORTEX →

Instant setup, no code required.

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