// SCAN REPORT

AI Cognitive Nexus

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

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

Last updated: 11 Jun 2026

14 can modify or destroy data

8 read-only

22 tools total

Community server · catalogue entry verified 11/06/2026

How to control AI Cognitive Nexus ↓

TOOL MAP

What AI Cognitive Nexus exposes to your agents

Read (8) Write / Execute (10) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous AI Cognitive Nexus tools

Destructive · High delete_agent Deletion of agents is an irreversible operation that destroys data and can cause cascading failures in dependent teams. Destructive · High delete_persona This tool irreversibly removes persona records from the system. Destructive · High delete_product This tool permanently removes product records and associated knowledge bases without the ability to undo the action. Destructive · High delete_team This tool permanently removes team configuration data, which cannot be undone.

14 of AI Cognitive Nexus's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AI Cognitive Nexus

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

Deny destructive operations

{
  "delete_agent": {
    "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

{
  "start_session": {
    "limits": [
      {
        "counter": "start_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_agent": {
    "limits": [
      {
        "counter": "get_agent_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 AI Cognitive Nexus — 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 AI COGNITIVE NEXUS →

Free to start. No card required.

FULL CATALOGUE

All 22 AI Cognitive Nexus tools

DESTRUCTIVE 4 tools

Destructive delete_agent 删除一个角色(Agent)。警告：这可能导致依赖此角色的团队失效。 Destructive delete_persona 删除一个指定的人物记录。 Destructive delete_product 删除一个指定的产品记录及其知识库。 Destructive delete_team 删除一个团队的配置。

EXECUTE 1 tools

Execute run_ai_team 运行指定的AI团队开展业务讨论。请注意这个环节需要耗费较长的时间，请告知用户耐心等待

WRITE 9 tools

Write start_session 创建新的session用于存储和跟踪会话，每个会议或讨论都应该创建一个新的session。 Write create_agent 创建一个新的角色(Agent)。 Write create_persona 根据定义的Schema创建一个新的人物。 Write create_product 根据定义的Schema创建一个新产品。 Write create_team 创建一个新的团队。 Write update_agent 更新一个已存在角色的信息。 Write update_persona 更新一个已存在人物的部分或全部信息。只提供需要修改的字段。 Write update_product 更新一个已存在产品的信息。只提供需要修改的字段。 Write update_team 更新一个已存在团队的配置。

READ 8 tools

Read get_agent 获取指定角色的配置信息。 Read get_persona 获取指定人物的完整详细信息。 Read get_product 获取指定产品的完整详细信息，包括其知识库。 Read get_team_config 获取指定团队的配置信息（非运行实例）。 Read list_agents 列出所有已定义的角色(Agent)。 Read list_personas 列出所有可用的人物信息记录，获取人物信息记录的 key 以加载个人信息。 Read list_products 列出所有已记录的产品。 Read list_teams 列出所有已配置的团队。

EXPLORE

Related servers

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

FAQ

Questions about AI Cognitive Nexus

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

Yes. The AI Cognitive Nexus server exposes 4 destructive tools including delete_agent, delete_persona, delete_product. 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 AI Cognitive Nexus? +

The AI Cognitive Nexus server has 9 write tools including start_session, create_agent, create_persona. 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 AI Cognitive Nexus.

How many tools does the AI Cognitive Nexus MCP server expose? +

22 tools across 4 categories: Destructive, Execute, Read, Write. 8 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on AI Cognitive Nexus? +

Register the AI Cognitive Nexus 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 AI Cognitive Nexus tool call.

Deterministic rules across all 22 AI Cognitive Nexus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AI COGNITIVE NEXUS →

Free to start. No card required.

22 AI Cognitive Nexus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.