Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tobewont/monitor-mcp-server --skill monitor-querygit clone --depth 1 https://github.com/Tobewont/monitor-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tobewont/monitor-mcp-server/monitor-query)<a href="https://agentmods.dev/skills/tobewont/monitor-mcp-server/monitor-query"><img src="https://agentmods.dev/badge/skills/tobewont/monitor-mcp-server/monitor-query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tobewont/monitor-mcp-server/monitor-query"><img src="https://agentmods.dev/badge/skills/tobewont/monitor-mcp-server/monitor-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.03268 |
| Opus 5.5 | $0.00045 | $0.01307 |
| Sonnet 5.5 | $0.00022 | $0.00654 |
| Haiku 4.5 | $0.00011 | $0.00327 |
Grade A, and why
monitor-query scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### 方式 C：curl 直接调用（streamable-http 模式） How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor Query Skill
通过 Monitor MCP Server 智能查询 Prometheus 兼容后端的指标数据。
本 Skill 支持多种 MCP 调用方式，适配不同客户端环境。
进阶参考：消歧策略、step 选取、PromQL 模式、常见问题排查等深度内容请阅读
references/reference.md。当用户的查询涉及 cluster/namespace/pod 命名歧义、长时间范围趋势分析或非常规 PromQL 时，先查阅 reference 文档。
环境变量
使用本 Skill 前，需确认以下环境变量已配置（由用户或部署环境提供）：
| 变量 | 说明 | 示例 |
|---|---|---|
MONITOR_MCP_SERVER_URL |
MCP Server 的访问地址，路径需与服务端 PROMETHEUS_MCP_PATH 一致（默认 /mcp，SSE 模式如使用自定义路径需相应调整） |
http://monitor.example.com:8000/mcp |
MONITOR_MCP_SERVER_NAME |
IDE 中注册的 MCP Server 名称（方式 A 需要） | user-monitor-mcp-server |
MONITOR_MCP_AUTH_TOKEN |
MCP Server 的认证 Token（可选，需认证时使用） | Bearer xxxx |
以下示例中的
${MONITOR_MCP_SERVER_URL}和${MONITOR_MCP_SERVER_NAME}均引用上述变量，请替换为实际值。
MCP 调用方式
根据你的运行环境，选择以下任意一种方式调用 MCP 工具：
方式 A：Cursor / IDE 内置 MCP（CallMcpTool）
在 Cursor 等已配置 MCP Server 的 IDE 中，直接通过内置工具调用：
CallMcpTool → server: ${MONITOR_MCP_SERVER_NAME}, toolName: <工具名>
arguments: { ... }
示例：
CallMcpTool → server: ${MONITOR_MCP_SERVER_NAME}, toolName: execute_query
arguments: { "query": "k8s:pod:cpu:used:percent{namespace=\"operation-devops-prod\"}" }
方式 B：mcporter CLI
通过 mcporter 命令行工具连接远程 MCP Server（SSE / streamable-http 模式）：
# 列出工具
mcporter list ${MONITOR_MCP_SERVER_URL} --allow-http
# 调用工具
mcporter call '${MONITOR_MCP_SERVER_URL}.<工具名>(<参数>)' --allow-http
示例：
# 列出所有指标
mcporter call '${MONITOR_MCP_SERVER_URL}.list_metrics(page_size: 0)' --allow-http --output json
# 获取指标标签
mcporter call '${MONITOR_MCP_SERVER_URL}.get_metric_labels(metric: "k8s:pod:cpu:used:percent")' --allow-http
# 即时查询
mcporter call '${MONITOR_MCP_SERVER_URL}.execute_query(query: "k8s:pod:cpu:used:percent{namespace=\"operation-devops-prod\"}")' --allow-http
# 范围查询
mcporter call '${MONITOR_MCP_SERVER_URL}.execute_range_query(query: "k8s:pod:cpu:used:percent{pod=~\".*drama.*\"}", start: "2026-04-16T00:00:00Z", end: "2026-04-16T06:00:00Z", step: "5m")' --allow-http
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 281 lines · 112 tokens per session scan A 643f54dfced0
monitor-query is a skill published in the GitHub repository Tobewont/monitor-mcp-server (2 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 3,268 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
monitor-query compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| monitor-queryTobewont/monitor-mcp-server | Skill | 2 | 4mo ago | MIT | A | 112 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 23k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |