// SCAN REPORT

Unified MCP Server

39 tools. 12 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

12 can modify or destroy data

27 read-only

39 tools total

Community server · catalogue entry verified 03/07/2026

How to control Unified MCP Server ↓

TOOL MAP

What Unified MCP Server exposes to your agents

Read (27) Write / Execute (11) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Unified MCP Server tools

Destructive · High ollama_rm This tool performs an irreversible deletion operation ('Remove a model'). Execute · High ollama_run The tool executes code or model inference operations via Ollama, which can produce arbitrary outputs based on input prompts. Execute · High ollama_serve Starting an Ollama server is an Execute-category action because it triggers an external operation (service startup) whose effects depend on system configuration and potentially on what models/processes the server subsequ Execute · Medium code_complete This tool generates code completions, which is primarily a Write/Read operation producing code artifacts.

12 of Unified MCP Server's 39 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Unified MCP Server

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

Deny destructive operations

{
  "ollama_rm": {
    "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

{
  "code_plan": {
    "limits": [
      {
        "counter": "code_plan_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "code_analyze": {
    "limits": [
      {
        "counter": "code_analyze_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 Unified MCP Server — 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 UNIFIED →

Instant setup, no code required.

FULL CATALOGUE

All 39 Unified MCP Server tools

DESTRUCTIVE 1 tools

Destructive ollama_rm Remove a model

EXECUTE 7 tools

Execute code_complete 智能补全未完成的代码，根据上下文和代码意图生成后续代码。适用于函数补全、逻辑补全等场景。 Execute code_generate 根据自然语言描述生成Python或JavaScript代码。支持生成函数、类、组件等各种代码结构，可指定代码风格。 Execute code_tdd 以测试驱动开发(TDD)专家的身份，指导开发流程。确保先写测试后写实现，并覆盖所有边界情况和异常路径。 Execute ollama_chat_completion OpenAI-compatible chat completion API Execute ollama_run Run a model Execute ollama_serve Start Ollama server Execute poetry_generate 根据主题、风格和长度生成中国古典诗词。可以生成唐诗、宋词、元曲等不同风格的诗词。

WRITE 4 tools

Write code_plan 为复杂的功能开发、架构变更或大规模重构创建详细的实施计划。包括需求分析、步骤分解、风险评估和测试策略。 Write ollama_cp Copy a model Write ollama_create Create a model from a Modelfile Write ollama_push Push a model to a registry

READ 27 tools

Read code_analyze 分析Python或JavaScript代码的结构、复杂度、质量问题和潜在改进点。提供详细的代码分析报告，包括性能、可读性、最佳实践等方面的评估。 Read code_architect 作为资深软件架构师，对系统设计、技术选型和架构决策提供专业咨询。生成架构决策记录(ADR)并评估权衡。 Read code_debug 识别代码中的Bug、逻辑错误或潜在问题，提供详细的问题分析和修复建议。支持调试运行时错误和逻辑错误。 Read code_explain 详细解释代码的工作原理、逻辑流程和实现细节。适合学习理解复杂代码或向他人讲解代码功能。 Read code_improve 优化和重构现有代码，提供性能改进、可读性提升、安全性增强等方面的具体建议和优化后的代码。 Read code_review 全面审查代码质量，包括最佳实践遵循度、安全漏洞、性能问题、代码异味等。提供优先级排序的改进建议。 Read code_test_generate 为给定代码自动生成单元测试。支持pytest、unittest(Python)和Jest、Mocha(JavaScript)等测试框架。 Read fashion_accessory_matches Get accessory (bags/shoes) matching suggestions Read fashion_color_combinations Get color combination suggestions for a base color Read fashion_outfit_suggestions Get outfit suggestions based on style and occasion Read fashion_style_analysis Get analysis and advice for a specific style Read history_culture_query 查询中国历史文化知识,包括制度、科技、艺术、风俗等方面的历史背景和发展。 Read history_dynasty_query 查询中国历史朝代的详细信息,包括朝代时间、重要事件、文化特点等。 Read history_event_query 查询中国历史事件的详细信息,包括事件背景、经过、影响等。 Read history_person_query 查询中国历史人物的详细信息,包括生平、主要成就、历史影响等。 Read ollama_list List models Read ollama_pull Pull a model from a registry Read ollama_show Show information for a model Read poetry_continue 根据给定的诗句接续下一句,保持韵律和意境的连贯性。 Read poetry_explain 详细解释一首中国古典诗词的含义、背景、艺术手法和文化内涵。 Read poetry_qa 回答关于中国古典诗词的问题,包括诗人生平、诗词流派、创作背景、格律知识等。 Read system_config Get current configuration Read system_health Get system health information Read zhouyi_cast_hexagram 起卦并解读。根据问题进行周易占卜，生成卦象并提供详细解读。支持多种起卦方式（随机、时间、手动）。 Read zhouyi_explain_hexagram 详细解释某个卦象的含义、卦辞、象辞、爻辞等传统文献内容，以及其在不同情况下的应用。 Read zhouyi_interpret 解读已有的卦象。对特定的卦象进行深入分析和解读，结合用户的问题给出建议。 Read zhouyi_qa 回答关于周易的问题，包括周易理论、卦象知识、占卜方法、历史背景等各方面的问题。

EXPLORE

Related servers

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

FAQ

Questions about Unified MCP Server

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

Yes. The Unified MCP Server server exposes 1 destructive tools including ollama_rm. 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 Unified MCP Server? +

The Unified MCP Server server has 4 write tools including code_plan, ollama_cp, ollama_create. 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 Unified MCP Server.

How many tools does the Unified MCP Server MCP server expose? +

39 tools across 4 categories: Destructive, Execute, Read, Write. 27 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Unified MCP Server? +

Register the Unified MCP Server 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 Unified MCP Server tool call.

Deterministic rules across all 39 Unified MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UNIFIED →

Instant setup, no code required.

39 Unified MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.