keith-apis-mcp
This MCP server exposes 11 tools for reading web content, generating share images, parsing jobs/resumes, matching resumes to jobs, and computing or predicting skill ratings.
Fetch public web pages as clean Markdown (respecting robots.txt), convert supplied HTML to Markdown, and get link previews/Open Graph metadata.
Generate 1200×630 PNG Open Graph share images with themes, badges, subtitles, and footers.
Parse individual or batched job postings into structured fields such as seniority, function, remote regions, salary, experience, skills, and flags.
Parse resumes from text or local PDF/DOCX/TXT files (max 5 MB, no OCR) into structured JSON.
Score a resume against a job on a 0–100 scale with breakdowns and matched/missing skills.
Compute skill ratings with OpenSkill, Glicko-2, Elo, or custom algorithms for 1v1, teams, free-for-alls, and draws.
Predict matchup win probabilities and match quality, and list supported rating algorithms and parameters.
Routes all of the server's requests through RapidAPI using a single RapidAPI key, which authorizes and meters access to the five hosted APIs behind the tools (web page to Markdown, OG image generation, job posting parsing, resume parsing and job matching, and skill rating).
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., "@keith-apis-mcp read https://example.com/blog/post as markdown and summarise it in five bullets"
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.
keith-apis-mcp: web page to Markdown, OG images, job and resume parsing, Elo ratings
keith-apis-mcp is an MCP (Model Context Protocol) server that gives AI assistants such as Claude, Cursor and ChatGPT eleven tools from five small hosted APIs: read any web page as clean Markdown, get link previews, generate Open Graph share images, parse job postings and resumes, score a resume against a job, and compute Elo, Glicko-2 or OpenSkill ratings. One RapidAPI key works for all of them, and each API has a free plan.
Tools
Tool | What it does | API |
| Fetch a page and return its main content as clean Markdown (for reading, summarising, RAG) | |
| Convert HTML you already have to Markdown | Web Page API |
| Title, description, images, favicon, Open Graph and Twitter card tags | Web Page API |
| 1200×630 PNG Open Graph image from a title (returned as an image) | |
| Job ad → seniority, job function, remote regions, annualised salary, skills | |
| Up to 20 postings in one call | Job Posting Parser |
| Resume (text, or a local PDF / DOCX / TXT file) → structured JSON | |
| 0–100 fit score with a breakdown and missing skills | Resume Parser + Job Match |
| Ratings from match results: OpenSkill, Glicko-2 or Elo; 1v1, teams, free-for-alls | |
| Win probability and match quality for a matchup | Skill Rating API |
| Supported algorithms and their parameters | Skill Rating API |
Related MCP server: Web2MD
Setup
Get a RapidAPI key and subscribe (free plans available) to the APIs you want, from each API's page linked above.
Add the server to your client with your key as
RAPIDAPI_KEY.
Claude Code
claude mcp add keith-apis -e RAPIDAPI_KEY=your-key -- npx -y keith-apis-mcpClaude Desktop, Cursor, Windsurf and other clients (claude_desktop_config.json, .cursor/mcp.json, ...):
{
"mcpServers": {
"keith-apis": {
"command": "npx",
"args": ["-y", "keith-apis-mcp"],
"env": { "RAPIDAPI_KEY": "your-key" }
}
}
}Requires Node.js 18 or newer.
Example prompts
"Read https://example.com/blog/post as Markdown and summarise it in five bullets."
"Make an OG image titled 'Release notes: October' with the light theme and footer example.com."
"Parse this job ad and tell me the salary range per year and whether it's open to Europe."
"Score my resume at ~/cv.pdf against this job description and list the skills I'm missing."
"Here are our league results; rank the players with Glicko-2 and predict next week's final."
Free tools
Try two of the APIs in a browser, with no key:
URL to Markdown converter: what
fetch_url_as_markdownreturns for a page.Elo rating calculator: win probability and new ratings for one game, the 1v1 case of
rate_matches.
Privacy
The server runs on your machine and sends each request only to the API it uses, through RapidAPI. The APIs are stateless: inputs, including resumes, are processed and returned, never stored or logged.
FAQ
Which tool should an AI agent use to read a web page?
fetch_url_as_markdown. It strips navigation, ads and boilerplate, so the model gets the article text at a fraction of the tokens of raw HTML.
Do I need all five subscriptions? No. Subscribe only to the APIs you use; tools for the others return a clear "not subscribed" error.
Can I use these without MCP? Yes. Each API is a normal REST API on RapidAPI, and each also runs as a pay-per-result Actor on the Apify Store.
License
MIT
Available Tools
11 toolsfetch_url_as_markdownWeb page to MarkdownARead-only
Fetch a public web page and return its main content as clean Markdown (navigation, ads and boilerplate removed), with the title and metadata. Use it to read an article or docs page for summarising, quoting or RAG. Respects robots.txt.
Inputs: url (required), max_chars, include_links, include_images.
generate_og_imageGenerate Open Graph imageARead-onlyIdempotent
Render a 1200x630 PNG Open Graph (og:image) share image from a title, for link previews on X, LinkedIn, Facebook, Slack and Discord. Returns the image.
Inputs: title (required), badge, theme, footer, +1 more.
get_link_previewLink previewBRead-only
Get a link preview for a URL: title, description, canonical URL, images, favicon, site name, Open Graph and Twitter card tags.
Inputs: url (required).
html_to_markdownHTML to MarkdownARead-onlyIdempotent
Convert HTML you already have into clean Markdown of its main content. Nothing is fetched.
Inputs: html (required), base_url, max_chars, include_links, +1 more.
list_rating_algorithmsList rating algorithmsARead-onlyIdempotent
List the supported rating algorithms and their tunable parameters with defaults and ranges.
Inputs: no named parameters.
match_resume_to_jobScore a resume against a jobARead-onlyIdempotent
Score how well a resume fits a job posting, 0-100, with a breakdown (skills, seniority, job function, experience, location) and the matched and missing skills.
Inputs: job (required), resume (required).
parse_job_postingParse a job postingARead-onlyIdempotent
Parse a job ad into structured fields: normalized title, seniority, job function, remote type and allowed regions, salary (min/max, currency, annualised), years of experience, skills and flags.
Inputs: title (required), company, location, description.
parse_job_postings_batchParse job postings (batch)BRead-onlyIdempotent
Parse 1 to 20 job postings in one call; results come back in the same order.
Inputs: postings (required).
parse_resumeParse a resume / CVARead-onlyIdempotent
Parse a resume into structured JSON: contact details, current title, seniority, job function, experience, education and skills. Give either the text or a local file path (PDF with a text layer, DOCX or TXT, max 5 MB; no OCR). Nothing is stored.
Inputs: text, file_path.
predict_matchPredict a matchupBRead-onlyIdempotent
Predict each team's win probability and the match quality (how even it is) from current ratings.
Inputs: teams (required), params, players, algorithm.
rate_matchesRate match resultsARead-onlyIdempotent
Compute player skill ratings from match results with OpenSkill, Glicko-2 or Elo. Handles 1v1, teams, free-for-alls and draws. Stateless: pass earlier ratings back in as players to continue.
Inputs: matches (required), params, players, algorithm.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Within each domain cluster the tools are clearly distinct: parse_job_posting vs parse_job_postings_batch (single vs batch), fetch_url_as_markdown vs html_to_markdown (fetch vs local convert), rate_matches vs predict_match. The only mild confusion is fetch_url_as_markdown vs html_to_markdown, but descriptions clarify that one fetches and one doesn't.
Almost all tools use snake_case verb_noun phrasing (parse_resume, get_link_preview, generate_og_image, match_resume_to_job). Minor deviations are noun-first names like html_to_markdown, but overall the convention is predictable and readable.
11 tools is a well-scoped count and each tool earns its place within its own cluster. The issue is not the number but the unrelatedness of the clusters, so the count itself is reasonable.
The recruiting pipeline (parse resume, parse job posting, batch, match) and the web-content cluster (fetch, convert, preview, OG image) are fairly complete, and the ratings trio is self-contained. However, the server is a grab-bag of three unrelated domains with no tool bridging them, making overall 'purpose' coverage hard to assess and leaving each domain somewhat shallow.
Maintenance
Related MCP Connectors
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Email validation, link previews and article-to-Markdown extraction for AI agents
Turn any webpage into clean Markdown for LLM/agent pipelines. Free tier; paid 1 USDC = 1000 req.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to read clean Markdown from any URL and assess source quality with AI-readability scores.687 npm1MIT
- AlicenseAqualityBmaintenanceFetch any web page as clean Markdown or plain text, split it into heading-aware, token-bounded RAG chunks, convert raw HTML, and read page metadata. Uses the Web2MD API on RapidAPI with your own key (free BASIC plan).443 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI editors and agents to read public web pages as clean Markdown and convert URLs, HTML, or Markdown into PDF, Word, Markdown, HTML, or JSON documents.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to fetch public web pages and return their main content as clean Markdown, including JavaScript-rendered pages with navigation, ads, and boilerplate stripped. Supports OAuth sign-in and a read-only tool for pulling docs, articles, and product pages into chat or knowledge bases.547 npmMIT