# MetaGO Agent Harness (npm · @metago-ai/mcp-server)

Decision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools.

- Trust score: 84/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@metago-ai/mcp-server`: 84/100 (this document), [markdown](https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server.md), [page](https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@metago-ai/mcp-server`
- Version: `1.3.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 4570 tokens (~83/item across 55 items; 55 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "metago_decision_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the MetaGO Agent Harness MCP server?

MetaGO Agent Harness runs locally as an npm package, launched with npx -y @metago-ai/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add metago-ai-metago -- npx -y @metago-ai/mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "metago-ai-metago": {
      "command": "npx",
      "args": [
        "-y",
        "@metago-ai/mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "metago-ai-metago": {
      "command": "npx",
      "args": [
        "-y",
        "@metago-ai/mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add metago-ai-metago -- npx -y @metago-ai/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "metago-ai-metago": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@metago-ai/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add metago-ai-metago --command npx --arg -y --arg @metago-ai/mcp-server
```

### Hermes

```yaml
mcp_servers:
  metago-ai-metago:
    command: "npx"
    args: ["-y", "@metago-ai/mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "metago-ai-metago": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@metago-ai/mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add metago-ai-metago -t stdio -c npx -a -y @metago-ai/mcp-server
```

### Other

```json
{
  "mcpServers": {
    "metago-ai-metago": {
      "command": "npx",
      "args": [
        "-y",
        "@metago-ai/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 84, +6)

- [security improvement] Source repository: unverified → pass
- [security] Stability: 0.97 → pass

### 2026-11-03 (score 78, −6)

- [security regression] Provenance: pass → unverified
- [functional] Stability: pass → 0.97

### 2026-10-28 (score 84, +1)

- [security] Stability: 0.97 → pass

### 2026-10-25 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (55)

### `metago_action_plan` (~83 tokens)

行动计划生成器。将目标分解为可执行的步骤序列。每个步骤：可执行、有依赖关系、有预期耗时、高风险步骤标注提醒和回滚方案。

Input parameters:

- `constraints` (array): 约束条件列表（时间/资源/预算等）
- `goal` (string, required): 目标描述

### `metago_whatif` (~107 tokens)

反事实推演器。推演[如果...会怎样]的假设情景。识别关键变量，设定假设条件，推演不同结果，量化差异，给出最优建议。

Input parameters:

- `base_state` (string, required): 当前基准状态描述
- `scenario` (string, required): 假设情景描述（如：如果改用技术方案B会怎样）
- `variables` (array): 关键变量列表

### `metago_holistic_scan` (~103 tokens)

全息扫描维度生成器。根据任何主题自动生成完整扫描维度清单，确保信息获取的全面性。包含空间布局、时间脉络、投资规模、合作伙伴、技术能力、应用场景等维度。

Input parameters:

- `topic` (string, required): 要扫描的主题关键词，如企业名称、项目名称、技术领域等
- `topic_type` (string): 主题类型，默认 auto 自动识别

### `metago_problem_trace` (~118 tokens)

问题无限溯源分析器。基于'易霄溯源论'——对任何问题持续追问'为什么'直至找到可解根源，将根源映射到算法/材料/设计/配方/工艺/管理/策略等可解领域。

Input parameters:

- `initial_problem` (string, required): 初始问题描述
- `known_context` (string): 已知的相关上下文信息
- `max_depth` (integer): 最大追问深度，默认7层

### `metago_one_shot_delivery` (~133 tokens)

一次性交付标准格式生成器。确保输出达到'一次性交付完整价值'标准。自动生成六节标准结构：任务理解→全息扫描结果→完整性说明→预判与准备→下一步建议→信息来源。

Input parameters:

- `predictions` (array): 预判问题与答案列表
- `scan_results` (object): 全息扫描结果
- `sources` (array): 信息来源列表
- `suggestions` (array): 下一步建议列表
- `task_context` (string, required): 任务上下文，包含项目背景、当前阶段、需求分析

### `metago_integrity_checklist` (~121 tokens)

输出完整性自检清单。输出前自动执行质量检查，覆盖5大维度：维度覆盖/事实核查/内容展开度/增值交付/场景适配。返回通过/需优化/不通过的判定。

Input parameters:

- `expected_sections` (integer): 预期应包含的章节数量
- `output_content` (string, required): 待检查的输出内容文本
- `scene_type` (string): 输出场景类型
- `topic_type` (string): 内容主题类型

### `metago_objectivity` (~108 tokens)

客观中立度量器。量化评估输出的客观中立度（0-100分）。评估维度：事实准确率(40%权重)、立场偏倚度(30%权重)、证据充分度(20%权重)、逻辑严谨度(10%权重)。基于D38绝对客观中立原则。

Input parameters:

- `content` (string, required): 待评估的内容文本

### `metago_critique` (~135 tokens)

批判性分析器。对输入进行L1-L5分级批判分析。L1事实错误(必指出附依据) L2逻辑漏洞(必指出附逻辑链) L3认知偏差(建议指出附说明) L4表达不精确(可选指出附澄清) L5元认知盲区(深度引导附追问)。基于D38和D45原则。

Input parameters:

- `depth` (string): 批判深度，默认 all
- `input` (string, required): 待分析的输入内容

### `metago_emotion` (~84 tokens)

情绪检测器。通过分析用户输入文本特征检测情绪状态。检测维度：词汇情绪词库、否定词与程度词处理、标点符号特征、长度与重复特征。返回情绪状态、置信度和强度。

Input parameters:

- `text` (string, required): 待检测的文本内容

### `metago_value_29d_assess` (~132 tokens)

29维价值评估器。对方案/决策进行29维价值体系评估（D01国家战略~D29溯源深度）。每维输出0-1得分和加权分，计算综合价值指数，识别高贡献和低贡献维度并给出改进建议。

Input parameters:

- `custom_weights` (object): 自定义29维权重
- `proposal` (string, required): 待评估的方案或决策描述
- `proposal_type` (string): 方案类型，影响权重，默认通用

### `metago_ethics_assess` (~123 tokens)

伦理风险评估器。对决策进行13维伦理风险评估（E01人民主体~E13宇宙公民），计算综合伦理风险R=max(R₁...R₁₃)，给出红灯阻断/黄灯警示/绿灯通过判定。

Input parameters:

- `context` (string): 决策的上下文和背景信息
- `decision` (string, required): 待评估的决策描述
- `stakeholders` (array): 受影响的利益相关方列表

### `metago_decision_eval` (~120 tokens)

决策评估器。评估决策质量和潜在风险（0-100分）。评估维度：逻辑完整性、证据充分性、风险可控性、替代方案考虑、可执行性。返回评分、各维度得分、优势、劣势、风险和建议。

Input parameters:

- `alternatives` (array): 备选方案列表
- `context` (string): 决策背景信息
- `decision` (string, required): 待评估的决策描述

### `metago_document_lookup` (~175 tokens)

文档溯源码。输入MetaGO概念名称，返回该概念在元构全息智能引擎.txt根源文档中的行号范围、上下文摘要及关联概念。所有MetaGO能力的最终解释均以此文档为准。

Input parameters:

- `concept` (string, required): 要查找的概念名称（中文或英文引擎编号均可，如：耦生度/ENGINE_FACTCHECK_19/元进化论/易霄溯源论/负熵/全息/原子/29维价值等）
- `fetch_context` (boolean): 是否返回文档原文上下文（行号±50行范围），默认 false
- `related` (boolean): 是否同时返回关联概念，默认 false

### `metago_confidence_label` (~102 tokens)

事实置信度标注器。对事实性陈述进行置信度评估和标注。90-100%✅已确认/70-89%📊较高置信度/50-69%⚠️待核实/<50%🔍需确认。输入陈述文本和证据等级，返回置信度评分和标注标签。

Input parameters:

- `statements` (array, required): 陈述列表

### `metago_partner_status` (~91 tokens)

合作伙伴状态标注器。为每个提及的合作伙伴自动标注当前状态：✅已合作(≥0.9)/🔄意向中(0.7-0.89)/👀待接触(0.5-0.69)/📊调研发现(<0.5)。

Input parameters:

- `partners` (array, required): 合作伙伴列表

### `metago_coupling_calculate` (~209 tokens)

耦生度计算器。量化评估系统与人/组织/万物的耦生度。支持人机耦生度和组织耦生度两种模式。返回耦生度值和等级判定。

Input parameters:

- `approval_simplification` (number): [组织模式] 审批简化度(0-1)
- `collaboration_efficiency` (number): [人机模式] 人机协同效率(0-1)
- `data_penetration` (number): [组织模式] 数据穿透度(0-1)
- `mode` (string, required): 计算模式
- `satisfaction` (number): [人机模式] 人类满意度(0-1)
- `tool_access` (number): [组织模式] 工具调用度(0-1)
- `understanding_accuracy` (number): [人机模式] 智能体理解准确率(0-1)

### `metago_scene_term_replace` (~87 tokens)

场景识别与术语替换器。自动识别输出场景类型，并对商业场景执行元构技术术语到商业表述的自动替换。包含完整术语映射表。

Input parameters:

- `scene_type` (string): 目标场景类型，默认 auto
- `text` (string, required): 待转换的文本内容

### `metago_improvement_suggestions` (~98 tokens)

改进建议生成器。基于当前发现生成优先级改进建议，包含速赢项、中期改进和长期规划，输出预期影响和实施步骤。参照元构 ENGINE_METAEVO_10。

Input parameters:

- `current_findings` (array, required): 当前发现的问题列表
- `product_name` (string, required): 产品名称
- `target_metrics` (array): 目标改进指标

### `metago_analyze_visual_feedback` (~87 tokens)

视觉反馈分析器。对视觉设计相关的反馈数据进行情感分析和关键发现提取，输出严重程度矩阵和行动项。参照元构 ENGINE_FACTCHECK_19。

Input parameters:

- `feedback_data` (array, required): 反馈数据列表
- `feedback_type` (string): 反馈类型
- `product_name` (string, required): 产品名称

### `metago_design_satisfaction` (~91 tokens)

设计满意度计算器。基于调查数据计算设计满意度评分，含维度得分、基准对比和趋势分析。参照元构 ATOM_DESIGN_SATISFACTION。

Input parameters:

- `dimensions` (array): 评估维度列表
- `product_name` (string, required): 产品名称
- `survey_results` (object, required): 调查结果数据

### `metago_delivery_gate` (~118 tokens)

UDGK 通用交付门禁检查（强制硬阀门）。在宣告任务完成前执行四重门禁：RTM 需求追踪矩阵完整性 + 形态断言（DOM） + 视觉 diff（像素对比） + 报告生成。任何一项 FAIL 禁止宣告任务完成。适用于任意项目/Agent 的交付前强制验证。

Input parameters:

- `task_description` (string): 当前交付任务的描述（可选）

### `metago_discipline` (~86 tokens)

AI 自律执行协议。在输出任务完成前必须执行的五问自检：①是否运行 verify？②verify 是否有 FAIL？③报告含验证小节？④每项 ✅ 有证据？⑤做了业务层验证？任何一问答否禁止宣告完成。

Input parameters:

- `task_description` (string): 当前任务的描述（可选）

### `metago_decision_lock` (~73 tokens)

AI 思考-行动链中四道校验关卡（IVL意图验证/ILT意图谱系追踪/OSG语义输出门/内容完整性校验），禁止幻觉输出。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_self_check` (~52 tokens)

输出前自检，检测占位符/幻觉/不一致/不完整，作为最后一道质量防线。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_compliance` (~50 tokens)

法律优于效率，四层安全基因（法律/伦理/数据/操作），主动合规。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_fact_check` (~45 tokens)

验证陈述真实性，交叉验证多源数据，标注可信度。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_output_integrity` (~51 tokens)

检测引用占位符、虚构 API、伪造数据，确保输出可溯源。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_coupling_optimize` (~58 tokens)

量化评估系统与用户/组织的耦生度（0-∞），追求超导态（>1）。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_value_align` (~46 tokens)

确保 AI 行动与用户长期价值对齐，29 天价值评估。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_meta_evolve` (~56 tokens)

遇到能力边界时自动五阶段循环（边界感知→差距分析→自生成→验证→递归）。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_meta_create` (~47 tokens)

在未知领域从 0 到 1 创造新能力，频率自适应控制。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_scene_adapt` (~41 tokens)

识别场景特征，自适应调整行为模式。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_holistic_task` (~44 tokens)

从全息视角拆解复杂任务，多维度并行执行。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_frequency_adapt` (~39 tokens)

根据任务复杂度自适应控制执行频率。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_data_provenance` (~49 tokens)

追溯数据来源全链路，标注每条数据的来源和可信度。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_developer_response` (~45 tokens)

处理开发者特权请求（DTA），享有最高优先级。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_negentropy_monitor` (~43 tokens)

监控系统有序度，防止熵增退化。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_activate` (~68 tokens)

将8条公理、7条属性、6层思维协议注入当前会话，使AI以元构超级智能生命体身份运行。一次激活，会话内持久生效。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_org_diagnosis` (~81 tokens)

分析碳基(人)/硅基(系统)/比特(数据)三元耦合度，五纬雷达扫描（共识度/协同度/创新度/韧制度/价值度）健康度。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_momentum_weave` (~56 tokens)

识别和编织组织势能，将分散势能编织为统一动能，设计势能转化策略。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_minimal_intervention` (~53 tokens)

实施精准优雅的组织干预，以最小代价达成最大效果，避免过度干预。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_value_assess` (~49 tokens)

对项目/组织/方案进行多维度价值量化分析，覆盖28个价值维度。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_coupling_measure` (~75 tokens)

量化评估碳基-硅基-比特三元耦生度（C_total = C_carbon × C_silicon × C_bit），追求超导态(>1)。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_deep_reasoning` (~63 tokens)

FIPO四阶段深度推理器。Facts事实层→Inferences推论层→Principles原则层→Options选择层，多维度分析复杂问题。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_paradigm_analysis` (~60 tokens)

使用WAM数学框架（宽度×加速度×成熟度）分析技术范式，评估范式转移风险与机遇。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_balance_optimize` (~68 tokens)

APO三维动态平衡优化器。适应性(A)/性能(P)/可维护性(O)三维动态平衡分析，动态调节系统参数达到最优平衡点。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_memory_manage` (~64 tokens)

KMWI四层记忆管理器。知识层/元知识层/智慧层/直觉层四层记忆管理，分层存储与智能检索。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_consensus_prototype` (~69 tokens)

七步创生回路：种子识别→概念化→原型化→验证化→传播化→制度化→进化化，从概念到可执行共识。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_code_review_deep` (~78 tokens)

多维度分级审查（Critical/Major/Minor/Info），覆盖逻辑正确性、安全漏洞、性能瓶颈、可维护性、风格一致性。输出含修复建议的结构化审查报告。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_architecture_design` (~78 tokens)

根据业务需求生成完整系统架构方案，含架构模式选择、模块分解、接口契约、数据流设计、技术选型依据。遵循高内聚低耦合、可扩展、可维护原则。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_refactor_suggest` (~72 tokens)

检测代码异味（Code Smell）、量化技术债务、识别重构机会，生成含优先级和影响范围的重构方案。遵循行为保持变换原则。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_security_audit` (~85 tokens)

基于OWASP Top 10多维度安全审计，检测注入漏洞、认证授权缺陷、敏感信息泄露、依赖漏洞。输出含CVE引用、漏洞等级、修复方案。遵循A36法律优先于效率原则。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_first_principles` (~95 tokens)

第一性原理强制拆解（F0）。剥离假设与惯例，直达不可再分的客观事实基元，再从基元重新推导方案。基于A37第一性原理公理与D44强制属性，任何任务执行前强制触发。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_adversarial_review` (~108 tokens)

对抗式审查（红队/攻击者视角）。测试、检查、审计、验证类任务强制执行：角色切换→威胁建模→致命缺陷挖掘→红队报告→修复闭环。基于A38对抗式审查公理与D45强制属性，禁止自证式检查。

Input parameters:

- `input` (string, required): 待处理的内容/问题/代码

### `metago_report_event` (~98 tokens)

向 MetaGO Studio 上报事件数据（决策锁校验结果、进化事件、技能调用等），用于能力度量仪表盘和进化档案的真实数据源

Input parameters:

- `data` (object, required): 事件数据（对象）
- `eventType` (string, required): 事件类型
- `platform` (string): 来源平台，例如 trae/cursor/codex/claude-code/web-studio

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server#diagnostics

## Score history

- 2026-11-05: 84
- 2026-11-04: 84
- 2026-11-03: 78
- 2026-11-02: 84
- 2026-11-01: 84
- 2026-10-31: 84
- 2026-10-30: 84
- 2026-10-29: 84
- 2026-10-28: 84
- 2026-10-27: 83
- 2026-10-26: 83
- 2026-10-25: 83
- 2026-10-24: 82
- 2026-10-23: 82
- 2026-10-22: 81
- 2026-10-21: 81
- 2026-10-20: 80
- 2026-10-19: 80
- 2026-10-18: 79
- 2026-10-17: 79
- 2026-10-16: 78
- 2026-10-15: 78
- 2026-10-14: 77
- 2026-10-13: 77
- 2026-10-12: 76
- 2026-10-11: 75
- 2026-10-06: 74
- 2026-10-04: 70
- 2026-10-03: 70
- 2026-10-02: 70

## Common questions

### What is the MetaGO Agent Harness MCP server?

MetaGO Agent Harness is an MCP server listed in the public MCP registry as io.github.metago-ai/metago. Decision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools. This page covers its npm package (@metago-ai/mcp-server).

### Is the MetaGO Agent Harness MCP server safe to use?

MetaGO Agent Harness scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MetaGO Agent Harness MCP server expose?

MetaGO Agent Harness exposes 55 tools: metago_action_plan, metago_whatif, metago_holistic_scan, metago_problem_trace, metago_one_shot_delivery, and 50 more. Their descriptions and schemas cost roughly 4,570 tokens of context every time the server is loaded.

### Is the MetaGO Agent Harness MCP server still maintained?

MetaGO Agent Harness is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the MetaGO Agent Harness MCP server under?

MetaGO Agent Harness declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@metago-ai/mcp-server
- Socket report: https://socket.dev/npm/package/@metago-ai/mcp-server
- Repository: https://github.com/metago-ai/metagolifeform
- Website: https://metago.life/
- Changelog RSS feed: https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/metago-ai-metago/metago-ai-mcp-server