Refine Job Search
Server Details
Job search management: applications, interviews, offers, recruiter email, and company openings.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 62 tools
Tools are namespaced by domain, and descriptions aggressively cross-reference siblings (e.g. jobs.archive vs jobs.delete, following.pause vs following.unfollow, recommendations.dismiss vs recommendations.block), which helps a lot. However, the three parallel object models (indexed opening.id, Following row id, board job id) with tools like jobs.add, openings.add_to_board, following.openings.list and search.company_openings create real risk of misselection, and the inbox cluster (acknowledge/apply_suggestion/dismiss/decline) is only separable by reading long descriptions.
Nearly everything uses dotted snake_case namespaces with a terminal verb, giving a predictable hierarchy (following.openings.mark_read, jobs.offer.add_negotiation). Minor deviation: some tools put the verb first after the domain (jobs.mark_applied, jobs.refresh) while others nest resource-then-verb (jobs.interviews.add), so the pattern is not perfectly uniform.
62 tools is well beyond a comfortable surface for an agent to hold in context and choose among. While the domain is genuinely broad (search, following, inbox, board, offers, recommendations), several clusters could be consolidated (e.g. offer accept/decline/delete/negotiation variants, inbox acknowledge/apply/dismiss/decline).
Coverage is strong: full lifecycle for jobs, interviews, offers and negotiations, plus read/write paths for following, inbox, recommendations and search. Gaps are modest but real: no direct companies.get/list beyond search results and submissions, no way to compose a new outbound email (only reply), and no standalone interview listing outside jobs.get.
Available Tools
62 toolsaccount.agendaBRead-onlyIdempotentInspect
Get upcoming interviews and action items
Inputs: no named parameters. Returns: data, meta
companies.submissions.createAIdempotentInspect
Submit a missing company using its public HTTPS careers URL, supplied or confirmed by the user. Refine detects supported sources and processes openings asynchronously. This adds to the shared index, not to Following. Use companies.submissions.get for progress; follow separately once company.id is available.
Inputs: careers_url (required), company_name (required). Returns: data
companies.submissions.getARead-onlyIdempotentInspect
Read company submission progress. queued/detecting/processing means wait; ready means search again using the company name. unsupported means the careers source is not supported; failed means processing failed. Do not claim the company was added or invent jobs while it is still working.
Inputs: submission_id (required). Returns: data
following.digest.getARead-onlyIdempotentInspect
Read the user-wide Following email digest schedule. data is null if no schedule is configured. Company match filters are managed separately with following.update.
Inputs: no named parameters. Returns: data
following.digest.updateAIdempotentInspect
Set the user-wide Following email digest schedule after the user requests it. Requires Plus or Student. For a new schedule supply frequency, hour (0–23), timezone (IANA), and weekday (Sunday=0) when weekly. Existing schedules can be patched.
Inputs: hour, weekday, timezone, frequency. Returns: data
following.followAInspect
Follow an indexed company for future matching openings and company recommendations. Get company_id from Search, a ready submission, or a recommendation candidate_company.id. Specify at least one match; [{}] follows all new openings. This does not submit an unknown careers page or collect historical matches.
Inputs: filters (required), company_id (required). Returns: data
following.listARead-onlyIdempotentInspect
List all followed companies, their filters, state, and unread counts. Returns the full list without pagination. Following delivers future matching openings; use Search to browse jobs already in the index.
Inputs: no named parameters. Returns: data
following.openings.listARead-onlyIdempotentInspect
Read matching openings from followed companies. tab defaults to unread. Use the row id for marking read and nested opening.id for opening details or adding to the board. meta.unread_count/read_count cover the selected follow or all companies before view filters; meta.filtered_count covers the current filtered tab.
Inputs: q, tab, page, limit, +3 more. Returns: data, meta
following.openings.mark_all_readAIdempotentInspect
Mark all unread openings as read for one follow, or every followed company if follow_id is omitted. Includes every page and openings hidden by view filters. Confirm the scope with the user first. The API returns no affected count; do not invent one.
Inputs: confirmed (required), follow_id. Returns: message
following.openings.mark_readAIdempotentInspect
Mark one Following row as read. Use the row id from following.openings.list, not nested opening.id.
Inputs: follow_opening_id (required). Returns: data
following.pauseAIdempotentInspect
Pause future matching openings for this follow without deleting it. This does not stop shared company indexing or pause other follows.
Inputs: follow_id (required). Returns: data
following.resumeAIdempotentInspect
Resume a paused company follow.
Inputs: follow_id (required). Returns: data
following.unfollowADestructiveIdempotentInspect
Unfollow a company and remove its Following feed and recommendation source. Confirm with the user first. Board jobs remain. To pause temporarily instead, use following.pause.
Inputs: confirmed (required), follow_id (required). Returns: message
following.updateAIdempotentInspect
Replace all match filters for a followed company. Other follow settings are unchanged. Pass [{}] for all new openings. Pending means the new filters are being applied; old unread counts may change.
Inputs: filters (required), follow_id (required). Returns: data
inbox.acknowledgeADestructiveIdempotentInspect
Keep auto-applied inbox items as-is and finalize the automatic action. Confirm the specific items with the user first.
Inputs: ids (required), confirmed (required). Returns: data, meta
inbox.apply_suggestionADestructiveIdempotentInspect
Apply an inbox item's suggested action, such as adding an application to the board or recording a rejection. Confirm the specific action with the user first.
Inputs: item_id (required), confirmed (required). Returns: data, meta
inbox.declineADestructiveInspect
Queue decline replies to recruiter outreach. Depending on the user's preference this SENDS email from their address. Only call after the user explicitly approved declining these specific conversations.
Inputs: ids (required), confirmed (required), remember, preference. Returns: data, meta
inbox.dismissADestructiveIdempotentInspect
Dismiss inbox items you are not acting on (also marks the mail read in Gmail)
Inputs: ids (required), confirmed (required). Returns: data, meta
inbox.draft_replyARead-onlyIdempotentInspect
Generate an AI reply draft for an inbox item. Returns HTML for review; it does not send anything.
Inputs: kind (required), item_id (required). Returns: data, meta
inbox.getARead-onlyIdempotentInspect
Get one inbox item with its related job and application
Inputs: item_id (required). Returns: data, meta
inbox.get_threadARead-onlyIdempotentInspect
Fetch the full email thread for an inbox item
Inputs: item_id (required). Returns: data, meta
inbox.listARead-onlyIdempotentInspect
List email conversations Refine matched to your job search (applications, interviews, recruiter outreach)
Inputs: tab, page, limit, shelf, +3 more. Returns: data, meta
inbox.mark_readAIdempotentInspect
Clear an inbox item's unread-reply flag
Inputs: item_id (required). Returns: message
inbox.refreshAInspect
Check Gmail for new mail now; returns per-account sync status
Inputs: no named parameters. Returns: data, meta
inbox.send_replyADestructiveInspect
Send an email reply through the user's Gmail. This emails a real person from the user's address. Only call after the user has seen the exact message body and explicitly approved sending it.
Inputs: body (required), item_id (required), confirmed (required), draft_kind. Returns: data, meta
inbox.sync_statusARead-onlyIdempotentInspect
Per-account Gmail synchronization status, including current progress and last sync time
Inputs: no named parameters. Returns: data, meta
inbox.undoADestructiveIdempotentInspect
Undo an auto-applied inbox action. This can delete a board record that the automatic action created, so confirm with the user first.
Inputs: item_id (required), confirmed (required). Returns: data, meta
inbox.unsubscribeADestructiveInspect
Unsubscribe the user from this sender's mailing list via one-click list-unsubscribe. This changes the user's real email subscriptions; confirm with them before calling. Use it for unwanted bulk senders, not for a person you can simply decline.
Inputs: item_id (required), confirmed (required). Returns: message
integrations.connect_googleAInspect
Get a link for the user to connect Gmail to Refine or approve a missing Gmail permission. Refine selects the permission needed for the connected account. The connection happens in the browser with no Refine sign-in required. Share the link only with the owner of this Refine account.
Inputs: no named parameters. Returns: expires_at, connect_url, instructions
integrations.listARead-onlyIdempotentInspect
List connected Google accounts and their grant status. To connect a new account, use integrations.connect_google.
Inputs: no named parameters. Returns: data, meta
jobs.addCInspect
Add a new job to your journey
Inputs: title (required), company (required), url, source, +4 more. Returns: data, meta
jobs.archiveAIdempotentInspect
Hide a job from the active board without recording a rejection or closing the application
Inputs: job_id (required). Returns: data, meta
jobs.deleteADestructiveIdempotentInspect
Permanently delete a job and its application from the board. Confirm with the user first; it cannot be undone. To hide a job without recording a rejection or closure, use jobs.archive instead.
Inputs: job_id (required), confirmed (required). Returns: message
jobs.getBRead-onlyIdempotentInspect
Get details of a specific job
Inputs: job_id (required). Returns: data, meta
jobs.interviews.addCInspect
Log an interview for a job
Inputs: name (required), job_id (required), notes, location, +1 more. Returns: data, meta
jobs.interviews.deleteADestructiveIdempotentInspect
Permanently delete an interview from a job. Confirm with the user first; it cannot be undone.
Inputs: job_id (required), confirmed (required), interview_id (required). Returns: message
jobs.interviews.updateCIdempotentInspect
Update an existing interview
Inputs: job_id (required), interview_id (required), name, notes, +10 more. Returns: data, meta
jobs.listCRead-onlyIdempotentInspect
List jobs in your journey
Inputs: page, limit. Returns: data, meta
jobs.mark_appliedCDestructiveIdempotentInspect
Mark a job as applied
Inputs: job_id (required). Returns: data, meta
jobs.offer.acceptADestructiveIdempotentInspect
Accept the offer for a job. This is a major state change that closes out the search for this role; confirm with the user before calling. It does not email the employer.
Inputs: job_id (required), confirmed (required). Returns: data, meta
jobs.offer.add_negotiationBInspect
Log a negotiation event on an offer (counter-offer, update, etc.)
Inputs: job_id (required), event_type (required), notes, event_date, +3 more. Returns: data, meta
jobs.offer.createCInspect
Record a job offer with compensation details
Inputs: job_id (required), notes, currency, rsu_text, +13 more. Returns: data, meta
jobs.offer.declineADestructiveIdempotentInspect
Decline the offer for a job, a major state change; confirm with the user first. It does not email the employer.
Inputs: job_id (required), confirmed (required). Returns: data, meta
jobs.offer.deleteADestructiveIdempotentInspect
Permanently delete the offer recorded for a job (the job stays). Use only to fix a mistake, and confirm with the user first; it cannot be undone.
Inputs: job_id (required), confirmed (required). Returns: message
jobs.offer.delete_negotiationADestructiveIdempotentInspect
Remove a negotiation event from an offer
Inputs: job_id (required), event_id (required), confirmed (required). Returns: message
jobs.offer.updateCIdempotentInspect
Update the offer recorded for a job
Inputs: job_id (required), notes, currency, rsu_text, +13 more. Returns: data, meta
jobs.refreshAInspect
Queue a job posting to be re-scraped. The returned job may remain pending; use jobs.get later to inspect the refreshed state.
Inputs: job_id (required). Returns: data, meta
jobs.unarchiveAIdempotentInspect
Restore an archived job to the active board
Inputs: job_id (required). Returns: data, meta
jobs.updateCIdempotentInspect
Update a job in your journey
Inputs: job_id (required), url, notes, title, +6 more. Returns: data, meta
openings.add_to_boardAIdempotentInspect
Add an indexed opening to the board after the user chooses it. Uses opening.id, not the Following row ID. Returns the existing board job if already added. This does not apply to the employer or send email; it also marks any matching Following item as read.
Inputs: opening_id (required). Returns: data, meta
openings.getARead-onlyIdempotentInspect
Read an indexed opening, including its full description and qualifications. Use opening.id from Search or Following, not a follow-opening row ID.
Inputs: opening_id (required). Returns: data
persona.getARead-onlyIdempotentInspect
Get the user's persona: inferred job-search preferences and traits with an understanding score. Use it to tailor advice and searches.
Inputs: no named parameters. Returns: data, meta
recommendations.blockBIdempotentInspect
Dismiss a recommended company and block it from future recommendations
Inputs: recommendation_id (required). Returns: data, meta
recommendations.dismissCIdempotentInspect
Dismiss a recommended company
Inputs: recommendation_id (required), reason. Returns: data, meta
recommendations.feedbackAInspect
Record recommendation feedback to improve future suggestions. The historical feedback tag "watched" records that a company was followed; it does not create a follow. Use following.follow first. Dismiss/block/restore actions are separate tools.
Inputs: feedback_types (required), recommendation_id (required), interaction_source. Returns: data, meta
recommendations.getBRead-onlyIdempotentInspect
Get one recommended company with sources and persona fit
Inputs: recommendation_id (required). Returns: data, meta
recommendations.listARead-onlyIdempotentInspect
Discover companies recommended from the companies you follow. Optionally filter by source_company_id (company.id from following.list, not a follow ID). Returns one flat list plus per-source counts. To follow a recommendation, use following.follow with candidate_company.id and your chosen filters.
Inputs: page, limit, source_company_id. Returns: data, meta
recommendations.restoreAIdempotentInspect
Restore a dismissed or blocked recommendation
Inputs: recommendation_id (required). Returns: data, meta
search.company_openingsARead-onlyIdempotentInspect
Read all matching jobs for a company in a ready search, not just its three preview jobs. Continue with data.next_page until null. Use company.id from the search results.
Inputs: search_id (required), company_id (required), page, sort. Returns: data
search.createAInspect
Search indexed jobs or companies. Supply input OR query, not both. Natural-language searches return a search ID and processing state: use search.get later, without rapid polling. Keep the ID to paginate or update this same search. Empty query {} is All openings, currently sorted by newest without persona personalization.
Inputs: page, sort, view, input, +1 more. Returns: data
search.getARead-onlyIdempotentInspect
Read a search and its results, switch jobs/companies view, or fetch results.next_page. Pending/interpreting/processing means it is still working: do not create another search or poll rapidly. If missing_company_name is set, ask for its careers URL and use companies.submissions.create. Company rows contain samples, not all matching jobs.
Inputs: search_id (required), page, sort, view. Returns: data
search.updateAInspect
Update the existing search instead of creating another. Supply input OR the complete replacement query; omitted filters are cleared. Wait until the current search is ready or failed before updating it.
Inputs: search_id (required), page, sort, view, +2 more. Returns: data
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Your job search in one place: resumes, the jobs you track, daily matches, interviews, next step.
Job search tracker for Claude and ChatGPT: applications, interviews, follow-ups, company watch.
Track job applications: find the ones to follow up on, add jobs, update status, notes and steps.
Find jobs, improve resumes, prepare for interviews, and manage your application pipeline.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceManages job applications, companies, roles, statuses, deadlines, and reminders through natural language queries.-
- FlicenseAqualityDmaintenanceEnables tracking job applications through a pipeline, scheduling follow-ups, and summarizing job search progress via natural language.7-
- FlicenseAqualityDmaintenanceAutomates job outreach by finding companies, discovering contacts, generating personalized emails with AI, and tracking campaigns.9-
- FlicenseNot gradedqualityCmaintenanceEnables tracking job applications by connecting Gmail to retrieve emails, process job details, manage statuses, and generate statistics.-
Glama MCP Gateway
Add one secure layer between your agents and this server.