Skip to main content
Glama
deenesjakoruzh
notaprompt

reframed-mcp

by notaprompt
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

reframed-mcp

Reframed 的 MCP 服务器。从任何兼容 MCP 的代理工具中根据职位定制简历。

一个工具：reframed_tailor。接受您的简历（文件路径或原始文本）和职位描述。返回两个保留个人风格的版本和一份来源摘要。

获取 API 密钥

  1. 登录 reframed.works

  2. 前往 Settings → API Keys → Create key

  3. 复制您的密钥 (rt_live_...)

Related MCP server: CompleteMCP

安装

Claude Code

claude mcp add reframed -- npx -y reframed-mcp
export REFRAMED_API_KEY=rt_live_...

或者永久存储密钥：

mkdir -p ~/.config/reframed
echo "rt_live_..." > ~/.config/reframed/key

Claude Desktop

编辑 ~/Library/Application Support/Claude/claude_desktop_config.json：

{
  "mcpServers": {
    "reframed": {
      "command": "npx",
      "args": ["-y", "reframed-mcp"],
      "env": {
        "REFRAMED_API_KEY": "rt_live_..."
      }
    }
  }
}

重启 Claude Desktop。

Cursor

在 Cursor 设置 → Features → MCP 中：

{
  "reframed": {
    "command": "npx",
    "args": ["-y", "reframed-mcp"],
    "env": { "REFRAMED_API_KEY": "rt_live_..." }
  }
}

Continue.dev

在 ~/.continue/config.json 中：

{
  "mcpServers": [
    {
      "name": "reframed",
      "command": "npx",
      "args": ["-y", "reframed-mcp"],
      "env": { "REFRAMED_API_KEY": "rt_live_..." }
    }
  ]
}

使用方法

安装完成后，询问您的助手：

Tailor my resume at ~/resume.md to this job: [粘贴职位描述文本]

风格选项

style

您将获得

conservative

轻微编辑 — 使用您的原话，针对 ATS 优化

reframed

保留个人风格的重写 — 更强的框架感

both (默认)

两个版本 + 来源摘要

限制

  • 每个 API 密钥每小时 100 次调用

  • V1 版本不支持 .pdf 简历输入 — 请转换为 .md 或粘贴原始文本

  • 职位描述输入：粘贴原始文本（V2 版本将支持 URL 抓取）

许可证

MIT — 参见 LICENSE。 参见 NOTICE.md 获取致谢信息。

Available Tools

1 tool
reframed_tailorA

Tailor a resume to a specific job. Preserves your voice. Returns two versions and a provenance summary.

ParametersJSON Schema
NameRequiredDescriptionDefault
resumeYesFile path to a .md resume, or paste raw resume text. PDF not supported.
jdYesRaw job description text (paste from the posting).
styleNoWhich version to return. 'conservative' = light edits. 'reframed' = voice-preserving rewrite. 'both' = both (default).both

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses that the tool returns two versions and a summary and preserves user voice, but does not detail other behaviors like how it handles errors, rate limits, or the exact nature of 'provenance summary'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise and front-loaded. Three sentences cover purpose, key feature, output, and one constraint. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given schema covers all parameters, and no output schema, the description is mostly complete. It could include more detail on the output format (e.g., plain text vs structured) but is sufficient for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds value beyond schema by explaining the overall purpose and output. It also notes PDF incompatibility, which is absent from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Tailor' and resource 'resume', and specifies key aspects: preserves voice, returns two versions and a provenance summary. It distinctively describes the tool's purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description is clear about when to use the tool, though it doesn't explicitly exclude alternatives (but there are no sibling tools). It mentions 'PDF not supported' which is a useful constraint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedreframed_tailor
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no risk of confusion between tools.

Naming Consistency5/5

With a single tool, naming is trivially consistent; the name uses a clear verb_noun pattern.

Tool Count3/5

A single tool is at the low end of the typical range; while appropriate for a narrow purpose, it feels thin compared to most servers.

Completeness4/5

The tool covers its stated purpose of tailoring a resume but lacks additional supporting operations like job description retrieval or resume parsing.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers