reframed-mcp
The server tailors a resume to a job description, returning one or both rewritten versions and a provenance summary.
Input: Provide your resume as a Markdown file path or raw text (PDFs not supported) and the job description as raw text.
Styles:
conservative— light edits optimized for ATS.reframed— voice-preserving rewrite with stronger framing.both(default) — returns both versions.
Provenance summary: Shows how much of the tailored result remains your original words, with verifiable percentages and a signed receipt at
reframed.works/verify/<id>.Free tier: 3 tailors per week without sign-up or API key, counted by network address.
API key (optional): Supply
REFRAMED_API_KEYvia environment variable or config for higher quotas and a saved voice profile.API host override: Set
REFRAMED_API_BASEto target a preview deployment or local server.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@reframed-mcpReframe my resume at ~/resume.md for this job: Senior SWE at Acme"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
reframed-mcp
Tailor a resume to a job posting, from inside whatever agent you already use.
No account. No API key. Install it and ask.
Start
Claude Code
claude mcp add reframed -- npx -y reframed-mcpClaude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"reframed": {
"command": "npx",
"args": ["-y", "reframed-mcp"]
}
}
}Restart Claude Desktop.
Cursor
Settings → Features → MCP:
{
"reframed": {
"command": "npx",
"args": ["-y", "reframed-mcp"]
}
}Continue.dev
In ~/.continue/config.json:
{
"mcpServers": [
{
"name": "reframed",
"command": "npx",
"args": ["-y", "reframed-mcp"]
}
]
}Related MCP server: resume-tailor-mcp-server
Ask
Tailor my resume at ~/resume.md to this job: [paste the posting]
That's the whole thing.
What comes back
Two versions of the resume and a provenance summary — how much of the result is still your own words.
| What you get |
| Light edits — your words, shaped for the ATS |
| Voice-preserving rewrite — stronger framing |
| Both versions + provenance summary |
The provenance summary is backed by a signed receipt at
reframed.works/verify/<id> — the percentages are checkable, not just asserted.
The free tier
Three tailors a week. No sign-up, nothing to configure.
Counted per network address, on the same weekly window the site uses.
When they're gone, the tool says so and points at reframed.works/pricing.
Other limits:
.pdfresume input isn't supported — convert to.mdor paste raw textJob description goes in as raw text (URL scraping comes later)
For more than the free tier
An API key raises the ceiling to your plan's quota and runs the tailor against your saved voice profile.
Sign in at reframed.works
Settings → API Keys → Create key
Copy the key (
rt_live_...)
Then either export it:
export REFRAMED_API_KEY=rt_live_...Or write it once and forget it:
mkdir -p ~/.config/reframed
echo "rt_live_..." > ~/.config/reframed/keyWith a key present, calls run against the account. Without one, they run on the free tier. Nothing else changes.
Plans and quotas: reframed.works/pricing.
Pointing somewhere else
REFRAMED_API_BASE overrides the host — useful against a preview deployment or
a local server. Defaults to https://reframed.works.
License
Available Tools
1 toolreframed_tailorA
Tailor a resume to a specific job. Preserves your voice. Returns two versions and a provenance summary.
| Name | Required | Description | Default |
|---|---|---|---|
| resume | Yes | File path to a .md resume, or paste raw resume text. PDF not supported. | |
| jd | Yes | Raw job description text (paste from the posting). | |
| style | No | Which version to return. 'conservative' = light edits. 'reframed' = voice-preserving rewrite. 'both' = both (default). | both |
TDQS
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.
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.
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.
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.
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.
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 tool update
v1.0.0- First observed
reframed_tailor
TDQS
Scored across 1 tool
Only one tool exists, so there is no risk of confusion between tools.
With a single tool, naming is trivially consistent; the name uses a clear verb_noun pattern.
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.
The tool covers its stated purpose of tailoring a resume but lacks additional supporting operations like job description retrieval or resume parsing.
Maintenance
Related MCP Connectors
Generate tailored, ATS-optimized resume PDFs and cover letters from a job description, over MCP.
Analyze job listings against your resume, track applications, and generate cover letters.
Score and tailor your CV/resume against a job posting — for AI agents and humans, no-login trial.
Tailor a resume and write a cover letter as real Word .docx files from facts you stored once.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProcesses and manages applicant resumes, facilitates job searches, generates job-specific resumes, and creates tailored cover letters.1MIT
- FlicenseNot gradedqualityCmaintenanceHelps job seekers tailor their resume and generate cover letters against a specific job posting, powered by Claude.-
- FlicenseAqualityCmaintenanceEnables tailoring resumes to job descriptions by scraping JDs, applying rules, and generating optimized DOCX resumes.11-
- AlicenseNot gradedqualityBmaintenanceEnables resume review against job descriptions through a three-stage pipeline: match scoring, experience rewriting, and ATS optimization. Supports text or document uploads.3 npmMIT