Workopia — Job Search MCP Server

Render the full job-detail card for a specific job the user asks about. Use this whenever the user references a particular job from a prior search result — by number (#1, '1', 'first', 'the 3rd one', 'job 3'), by company name (partial or full, e.g. 'Morgan Stanley', 'Morstan'), by role/title phrase ('the analyst role', 'the credit risk one'), or by any 'show me this job' / 'tell me more about X' / 'view this role' style request. Resolving job_id from user reference: identify the right job from the most recent prior search/refine result (the numbered list you generated): (a) numeric/ordinal → the Nth job; (b) company name → substring match on Company field; (c) role/title phrase → substring match on Job Title field. Then pass that job's **Job Id** value from the prior search result's content text VERBATIM as job_id. Do NOT use a placeholder like 'JOB_1', '#1', or any synthetic id — only the real **Job Id** string from the prior result is server-valid. Required: job_id. OUTPUT BEHAVIOR: Render the response as a structured markdown card with the job's title (linked to the apply URL), company, location, salary, employment type, work mode, must-have skills, key requirements, highlights, and summary. Follow it with a brief next-step hint (e.g. 'Want to save it, find similar roles, ask about the company, or tailor your resume for this role?').

Search jobs across 90+ countries by title, location, salary, remote/hybrid work mode, or employment type. Find roles in tech, finance, product, design, marketing, and every other vertical — aggregated from 1000+ ATS sources globally. Default action is search; use refine when the user asks for more matches or gives feedback on a prior result set; use save to bookmark a job for the signed-in user (requires OAuth). REFINE PROTOCOL (action=refine has THREE distinct modes): (1) Pure continuation / 'show me more' / 'next batch' / 'another set' / 'more like these': pass refine_recommendations.exclude_ids = the full array of **Job Id** values from the most recent search/refine result's content text (verbatim) + refine_recommendations.session_id = prior response's session_id if present. Server returns next 10 unique jobs. (2) 'Show me more like #N' / 'similar to the Atlassian one' / 'jobs like #2': pass refine_recommendations.liked_indexes = [N] (1-based position from prior numbered list) + exclude_ids + session_id. Equivalently you may pass refine_recommendations.liked_job_ids = [<that job's **Job Id** value verbatim>]. Server seeds the recommendation from that job's title/skills/company profile. (3) 'Less like #N' / 'no more N-style jobs' / 'avoid jobs like that': pass refine_recommendations.disliked_indexes = [N] (or disliked_job_ids = [<Job Id>]) + exclude_ids + session_id. Server suppresses similar jobs. All three modes: if you skip exclude_ids, the user sees duplicates — that's a failure. The handler layers exclude_ids with server-side AgentKit memory, so partial lists still work. NEVER invent 'JOB_1' / '#1' as job_id values — always use the real **Job Id** string from the prior result's content text. For detail requests (user asks about a specific job from the list, e.g. 'details for #1', 'show me this job', 'tell me more about <company>'), DO NOT call this tool — call job_detail_tool instead. That separate tool binds to the job-detail widget card so the full job card renders in chat. OUTPUT BEHAVIOR: Render the search results as a numbered markdown list, one line per job, in this exact compact format: `N. **[Job Title](View_Job_URL)** — Company · Location · Job Type · Compensation · Posted MMM DD`. Embed the View Job URL as a markdown link on the title (so the user can click to apply). Keep URLs intact — don't strip parameters. Skip a field entirely if it's missing — never print 'N/A' placeholders. The numbered list IS the canonical user-facing answer. REQUIRED follow-up: after the list, output EXACTLY these two sentences as two parallel questions (same pattern for action=search and action=refine): Sentence 1 — 'Would you like to see full details on any of these? Reply with the number (#1), the company name, or the role title.' Sentence 2 — 'Or would you like to refine the list — what should change (work mode, level, salary, sector)?' These two sentences must be separate and parallel; do NOT merge them into one 'detail ... or refine' clause (that buries the detail CTA). Both questions must be asked every time after a search or refine result. When the user replies referring to a specific job from the list, identify which job they mean and call job_detail_tool immediately. Identifying the job (use flexibly — users rarely type '#N' literally): (a) any numeric or ordinal reference ('#1', '1', 'first', 'the 1st', 'top one', 'job 3', 'the third') → the Nth job in your prior numbered list; (b) a company name, partial or full ('Morgan Stanley', 'Morstan', 'Capital One') → case-insensitive substring match on the Company field of the prior list, pick the first match; (c) a role/title phrase ('the analyst role', 'the credit risk one') → case-insensitive substring match on the Job Title field. If multiple jobs match, prefer the earliest. Only if no reasonable match exists, ask a one-line clarifying question. Then pass that job's **Job Id** value from the prior search result's content text VERBATIM as job_id to job_detail_tool / tailor_resume_tool / cover_letter_tool. Do NOT invent a placeholder like 'JOB_1' or '#1' — those are not server-valid IDs. For save, pass job_id + optional job_title/company/job_url in save_job. Put search fields in search_jobs or parameters; refine in refine_recommendations; save in save_job.

Write a cover letter for a SPECIFIC job — TWO steps. STEP 1 (default; action omitted or 'prepare'): the server returns the job's JD and the candidate's background, plus writing instructions. YOU (the model) then WRITE the cover letter (250–350 words, specific to the role, mapping the candidate's real achievements to the JD — never fabricate). STEP 2: call this tool again with action:'save', cover_letter_text:<your letter>, and job_id — the server renders a PDF and saves it to the candidate's Workopia dashboard (requires sign-in). Use whenever the user asks for a cover letter for a specific job. Resolving job_id (same rules as tailor_resume_tool / job_detail_tool): pass the **Job Id** value from the most recent prior search/refine result VERBATIM; no placeholders like 'JOB_1' or '#1'. For STEP 1 supply ONE of job_id (preferred — server fetches the JD from Mongo) OR job_description, plus the candidate's resume via resume_text / resume_content / json_resume / user_profile.

Show the signed-in user's Workopia dashboard (saved, tailored, and applied jobs + latest resume). Requires OAuth. Default action is list; optional status_filter (all | saved | tailored | applied). Use whenever the user asks to recall their Workopia activity: 'my applications', 'what jobs have I saved / applied to / tailored', 'show my dashboard', 'where did I leave off'. Returns a secure link to open the full dashboard on the web.

Tailor a resume to a SPECIFIC job — TWO steps. STEP 1 (default; action omitted or 'prepare'): the server returns the job's full JD, its must-have skills/requirements, and the candidate's current resume, plus tailoring instructions. YOU (the model) then WRITE the tailored resume as JSON Resume, following the instructions — weave JD keywords into existing bullets only where the candidate genuinely has the experience, never fabricate experience/titles/dates/employers, keep all dates and company names, and flag any keyword you couldn't honestly add. STEP 2: call this tool again with action:'save', tailored_resume:<your JSON Resume>, and job_id — the server renders a PDF and saves it to the candidate's Workopia dashboard (requires sign-in). Use whenever the user references a specific job to tailor for: 'tailor for #1', 'for Morgan Stanley', 'tailor my resume for this role: <JD>'. Resolving job_id (same rules as job_detail_tool): from the most recent prior search/refine result — (a) numeric/ordinal → the Nth job; (b) company name → Company-field match; (c) role/title phrase → Job-Title match — then pass that job's **Job Id** value VERBATIM. Do NOT use placeholders like 'JOB_1' or '#1'. For STEP 1 supply ONE of job_id (preferred — server fetches the JD from Mongo) OR job_description, plus the candidate's resume via resume_text / resume_content / resume_data. For general 'improve my resume' (no specific job), do NOT call this tool — call resume_tool action=improve instead. Note: the tailored resume is written by your AI client's own model — the assistant you are already using — so it works out of the box with nothing to configure; Workopia runs no LLM of its own and never charges for the AI.