Upwork MCP server for AI agents
Let Claude, ChatGPT or your own agent read Upwork: 2 typed functions through one MCP server. No Upwork API key needed.
- Site
- upwork.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Upwork
An MCP server for Upwork alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/upworkEvery site
One MCP server for Upwork and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getJobReads one public Upwork job posting by the url or id searchJobs() returned: full description, budget, experience level, skills, proposals count and…Arguments
Name Type Required urlstringNo idstringNo Returns
UpworkJobinterface UpworkJob { id: string; title: string; url: string; datePosted: string | null; description: string; employmentType: string[]; clientCountry: string | null; applicantCountries: string[]; budget: string | null; experienceLevel: string | null; skills: string[]; proposals: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/upwork/getJobCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.upwork.getJob({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.upwork.getJob({}))curl -X POST https://api.bowmark.ai/v1/sites/upwork/getJob \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.upwork.getJob({});searchJobsSearches Upwork's public freelance job postings by keyword, as the Find Work search box does, and returns ~10 job rows per page.Arguments
Name Type Required querystringYes pagenumberNo Returns
UpworkJobSummary[]interface UpworkJobSummary { id: string; title: string; url: string; posted: string | null; budget: string | null; experienceLevel: string | null; duration: string | null; description: string; skills: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/upwork/searchJobsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.upwork.searchJobs({ query: "python" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.upwork.searchJobs({"query": "python"}))curl -X POST https://api.bowmark.ai/v1/sites/upwork/searchJobs \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"python"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.upwork.searchJobs({ query: "python" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/upwork/<function> - OpenAPI
/v1/sites/upwork/openapi.json