Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
MCPJam/inspector
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
上手GET STARTED
npx @mcpjam/inspector@latest选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01读写本地文件Reads and writes local filesreadme
| **Skills** | Extend models with reusable behaviors in Playground. Local skills are read from your filesystem and never leave you
02读取 API KeyReads an API key.agents/skills/server-change/SKILL.md
- Never log tokens, access links, API keys or request bodies that may hold them.
03读取 API KeyReads an API keysdk/skills/create-mcp-eval/SKILL.md
| **Save results to MCPJam** | `none`, `auto` (saves when MCPJAM_API_KEY is set), or `reporter` (shared EvalRunReporter). Use an MCPJam API
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
26 OCT 202626 OCT 2026
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
HN_STORY · 4 points · 0 comments
依赖：Dependencies:react-force-graph-2d
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
}
],
"apiKey": "generated on restart unless `MCPJAM_SESSION_TOKEN` is configured. See the [network access",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 7,
"indie-web": 0,
"skill-agent": 9,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "e on. - Flaky (passes on rerun locally, timing-based): note the test name in t",
"skillMdTotal": 14,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 1,
"devtool": 13,
"security": 1,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "14 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 16 markdown files",
"weight": 0.75
},
{
"signal": "MCP topic + README",
"weight": 0.6
}
],
"scannedSources": [
"readme",
".agents/skills/fix-ci/SKILL.md",
".agents/skills/investigate-production/SKILL.md",
".agents/skills/run-inspector/SKILL.md",
".agents/skills/server-change/SKILL.md",
".agents/skills/ui-change/SKILL.md",
".agents/skills/ui-copy/SKILL.md",
".agents/skills/verify-before-pr/SKILL.md",
"sdk/skills/create-mcp-eval/SKILL.md",
"sdk/skills/explore-to-sdk-evals/SKILL.md",
"skills/drive-mcpjam-playground/SKILL.md",
"skills/mcp-inspector/SKILL.md",
"skills/mcpjam-eval-import/SKILL.md",
"skills/run-mcpjam-evals/SKILL.md",
"skills/user-value-chain-glossary/SKILL.md"
],
"skillMdFetched": 14
}