MCP Server

Nico exposes a Model Context Protocol (MCP) server that lets AI assistants like Claude interact with Nico directly.

What can the MCP server do?

The MCP server provides 13 tools in three groups: job posting search (job_posting_*, discover openings in Nico’s index), job application management (job_application_*, your own tracked applications), and interviews (schedule and manage interviews on your applications).

Tool	Group	Type	Description
`job_posting_search`	Posting search	Read	Search Nico’s job postings index
`job_posting_get`	Posting search	Read	Get one posting’s full detail, incl. the application URL
`job_application_search`	Application mgmt	Read	Search your saved applications by URL (canonical) or company name
`job_application_list`	Application mgmt	Read	List your applications with filtering and pagination
`job_application_get`	Application mgmt	Read	Get full details of one application, incl. notes and interviews
`job_application_parse_url`	Application mgmt	Read	Extract structured data from a job posting URL
`job_application_create`	Application mgmt	Write	Add an application to your board (draft, or proposed)
`job_application_update`	Application mgmt	Write	Correct an application’s details (title, URL, salary, …)
`job_application_transition`	Application mgmt	Write	Move an application through its status lifecycle
`job_application_add_note`	Application mgmt	Write	Add a note to an existing application
`interview_list`	Interviews	Read	List interviews — all of them, or one application’s — with time filters
`job_application_add_interview`	Interviews	Write	Schedule an interview for an application
`interview_update`	Interviews	Write	Reschedule or edit an existing interview

Job posting search (job_posting_search, job_posting_get) searches Nico’s shared posting index — not your own applications. To check “have I already saved this?”, use job_application_search. Posting search requires job search to be enabled for your account.

Connecting your AI assistant

The server URL for all assistants is:

https://mcp.nico-jobagent.com/mcp

Authentication is handled via OAuth — you never paste a token, API key, or client ID. Nico supports dynamic client registration, so your assistant registers itself automatically. When you add the connector, you’re redirected to Nico’s consent screen; click Authorize and you’re connected.

Claude (Desktop and claude.ai)

Go to Settings → Connectors and choose Add custom connector.
Enter a name (e.g. “Nico”) and the server URL above. Leave the advanced OAuth fields blank.
Click Connect and approve access on Nico’s consent screen.

ChatGPT

Custom MCP connectors in ChatGPT require developer mode, which is available on paid plans (Plus, Pro, Business/Enterprise).

Enable developer mode: go to Settings → Apps & Connectors → Advanced settings and turn on Developer mode.
Go back to Apps & Connectors and choose Create to add a custom connector.
Enter a name (e.g. “Nico”), the server URL above, and select OAuth as the authentication method. Leave the client ID and secret blank — ChatGPT registers itself automatically.
Complete the connection and approve access on Nico’s consent screen.

For a visual walkthrough of enabling remote MCP servers in ChatGPT, see Enable Remote MCP Servers in ChatGPT (Step-by-Step).

The MCP server requires OAuth authentication with the mcp scope — the connector requests it automatically. See OAuth for details on the flow, scopes, and revoking access.

Job posting search

job_posting_search

Search Nico’s job postings index — the same data behind the in-app job search at /jobs. Returns the most recent matching postings, newest-first, in compact form (no application URL or description — fetch those with job_posting_get). Parameters:

Parameter	Type	Required	Description
`country_code`	string	Yes	ISO 3166-1 alpha-2 country code, e.g. `US` or `NL`. Always required.
`title`	string[]	No	Title phrases ORed together. Each phrase is a case-insensitive substring match, and a phrase that names a role also includes similar titles filed under it — see Similar titles below. Example: `["backend engineer", "staff engineer"]`
`title_exact`	boolean	No	`true` keeps every title phrase literal — no similar titles. Default `false`.
`title_levels`	integer	No	For a title phrase with a level word (`"senior software engineer"`): `0` (default) includes similar titles at that level only, `1` also takes one level up or down. Ignored when `title_exact` is `true`.
`region`	string	No	State/province name (case-insensitive). Required when `city` is set and `country_code` is `US` or `CA`.
`city`	string	No	City name for radius search. Looked up exactly against Nico’s geocoded locations index — no external geocoding is performed. Returns an error if the city is unknown or ambiguous.
`radius_km`	integer	No	Search radius in km around the resolved `city` (default `25`, max `250`). Only used when `city` is set.
`work_mode`	string[]	No	One or more of `remote`, `onsite`. Hybrid postings surface under either filter.
`employers`	string[]	No	Filter to postings at these employers. Pass employer names — lookup is case-insensitive. Each name must resolve to exactly one employer; unknown or ambiguous names return an error. Example: `["Anthropic", "Stripe"]`
`limit`	integer	No	Results per page (default `20`, max `100`).
`page`	integer	No	Page number (default `1`). Use the response’s `pagination` block to walk further pages.

Don’t combine a geographic filter (region or city) with work_mode: ["remote"]. Remote postings aren’t pinned to a location, so that combination almost always returns nothing. Search remote roles by country, and use region/city for on-site or hybrid roles.

City radius search: Pass city together with country_code (plus region for US/CA) to filter postings within radius_km of that city. Cities are resolved by exact, case-insensitive match against Nico’s existing geocoded-locations index — there is no live geocoding fallback, so unknown or ambiguous names return an error rather than a best-guess match.

{
  "city": "Amsterdam",
  "country_code": "NL",
  "radius_km": 50
}

{
  "city": "Springfield",
  "region": "Illinois",
  "country_code": "US",
  "radius_km": 50
}

Similar titles: A title phrase that names a role — "engineering manager", "software engineer" — also matches postings filed under that role whose title says it differently: "Software Engineering Manager", "Manager, Engineering". The widening stops at director level: "engineering manager" never pulls in "Director of Engineering" or "VP Engineering", and "director of engineering" matches only director and VP titles. A phrase with a level word — "senior software engineer", "staff software engineer" — widens to that role’s titles at the same level only: "Sr. Software Engineer", "Senior Platform Engineer", "Software Engineer III", "Senior Software Developer". Pass title_levels: 1 to take one level up or down as well (mid-level and staff titles for a senior phrase). Pass title_exact: true to keep every phrase literal. The response’s title_expansions says what widened — one entry per phrase, with level (null for a phrase without a level word) and every other title now included — so you can tell the user the search covered them:

{
  "title_expansions": [
    {
      "term": "senior software engineer",
      "canonical_title": "software engineer",
      "level": "senior",
      "examples": ["platform engineer", "software development engineer", "java developer"],
      "alias_count": 3
    }
  ]
}

It is empty when no phrase widened, and always empty under title_exact: true. Example response:

{
  "job_postings": [
    {
      "id": "019e1e37-ff01-7870-a56a-7b316b2d2373",
      "job_application": null,
      "title": "Senior Backend Engineer",
      "company_name": "Acme Co",
      "company_id": "019e1e37-aa01-7870-a56a-7b316b2d2374",
      "location": "San Francisco, CA / Hybrid",
      "work_mode": "hybrid",
      "employment_type": "full-time",
      "salary_min": 150000,
      "salary_max": 200000,
      "salary_currency": "USD",
      "salary_period": "annual",
      "posted_at": "2026-05-12T08:00:00Z",
      "effective_posted_at": "2026-05-12T08:00:00Z"
    }
  ],
  "count": 20,
  "sort": "newest",
  "pagination": {
    "current_page": 1,
    "per_page": 20,
    "total_count": 99,
    "total_count_capped": false,
    "next_page": 2
  },
  "title_expansions": []
}

total_count stops counting at 100 (total_count_capped is then true); walk further pages with next_page, which is null on the last page. sort is newest unless your account has ranked search, in which case a sort: "match" request returns match here and a match_rank on each result. Each result’s job_application is null until you have acted on that posting, otherwise the id and status of the application you already have. Search results omit url and description to stay compact. Take a result’s id and call job_posting_get to retrieve the application URL and the full description. Errors: The tool returns a single-key error object when the request can’t proceed:

{ "error": "country_code is required" }

Other error messages you may see:

country_code is required — country_code is mandatory on every call.
region (state/province) is required for city search in US (or CA) — region must be set when city is given and the country is US or CA.
Location not found: <city> — the city wasn’t found in Nico’s geocoded locations index.
Ambiguous location: multiple matches for <city> — please refine — more than one row matched; narrow with region.
Unknown employer: <name> — a name in employers didn’t match any employer.
Ambiguous employer: multiple matches for <name> — please refine — a name in employers matched more than one employer; refine the spelling.
Job search is not enabled for this account — the calling account doesn’t have job search enabled.

job_posting_get

Get one job posting by the id returned from job_posting_search. Returns the same fields as a search result, plus the external application url and the full description (the two fields the search list omits). Parameters:

Parameter	Type	Required	Description
`id`	string	Yes	The posting `id` from `job_posting_search` results.

Example response:

{
  "id": "019e1e37-ff01-7870-a56a-7b316b2d2373",
  "title": "Senior Backend Engineer",
  "company_name": "Acme Co",
  "company_id": "019e1e37-aa01-7870-a56a-7b316b2d2374",
  "location": "San Francisco, CA / Hybrid",
  "work_mode": "hybrid",
  "employment_type": "full-time",
  "salary_min": 150000,
  "salary_max": 200000,
  "salary_currency": "USD",
  "salary_period": "annual",
  "posted_at": "2026-05-12T08:00:00Z",
  "effective_posted_at": "2026-05-12T08:00:00Z",
  "url": "https://acme.test/jobs/be-eng",
  "description": "About the role…"
}

Returns { "error": "Job posting not found" } for an unknown id. Same feature-flag gate as job_posting_search.

After finding a relevant posting, call job_posting_get for its url, then pass that URL to job_application_parse_url to extract richer structured fields, and finally job_application_create to add it to your board.

Job application management

job_application_search

Search your job applications by URL or company name (case-insensitive). URL matching is canonical: a tracking parameter, trailing slash, differently-cased host, fragment or email-forward wrapper all resolve to the same application, exactly as job_application_create’s duplicate check does. The two tools therefore always agree about whether a job is already tracked. Parameters:

Parameter	Type	Required	Description
`url`	string	No*	Search by job posting URL, matched canonically
`company_name`	string	No*	Search by company name (case-insensitive)
`status`	string	No	Filter results by status group: `draft`, `applied`, `interviewing`, `offer`, `finished`, `active`

*At least one of url or company_name is required. Example response (search by URL):

{
  "exists": true,
  "count": 1,
  "job_applications": [
    {
      "id": "019e1e40-1234-7000-9abc-1111aaaa2222",
      "title": "Senior Product Manager",
      "status": "applied",
      "company": { "name": "Acme Corp" }
    }
  ]
}

job_application_list

List your job applications with optional filtering and pagination. Parameters:

Parameter	Type	Required	Description
`status`	string	No	Filter by status group: `draft`, `applied`, `interviewing`, `offer`, `finished`, `active`
`page`	integer	No	Page number (default `1`)
`per_page`	integer	No	Items per page (default `25`, max `100`)

Example response:

{
  "job_applications": [
    {
      "id": "019e1e40-1234-7000-9abc-1111aaaa2222",
      "title": "Senior Product Manager",
      "url": "https://acme.com/careers/pm-senior",
      "status": "applied",
      "work_mode": "hybrid",
      "location": "Berlin, Germany",
      "company_name": "Acme Corp",
      "created_at": "2026-03-15T10:30:00Z",
      "updated_at": "2026-03-16T09:00:00Z"
    }
  ],
  "pagination": {
    "current_page": 1,
    "per_page": 25,
    "total_count": 52,
    "total_pages": 3
  }
}

job_application_get

Get the full details of one job application, including its notes and interviews. Parameters:

Parameter	Type	Required	Description
`id`	string	Yes	The job application `id`

Example response:

{
  "id": "019e1e40-1234-7000-9abc-1111aaaa2222",
  "title": "Senior Product Manager",
  "url": "https://acme.com/careers/pm-senior",
  "status": "applied",
  "work_mode": "hybrid",
  "location": "Berlin, Germany",
  "salary_min": 80000,
  "salary_max": 100000,
  "salary_currency": "EUR",
  "salary_period": "annual",
  "company": { "id": "019e1e37-aa01-7870-a56a-7b316b2d2374", "name": "Acme Corp", "url": "https://acme.com" },
  "notes": [],
  "interviews": [],
  "created_at": "2026-03-15T10:30:00Z"
}

Returns { "error": "Job application not found" } for an unknown id.

job_application_parse_url

Extract structured job data from a job posting URL. Nico automatically detects the job board and parses the posting. Parameters:

Parameter	Type	Required	Description
`url`	string	Yes	URL of the job posting to parse

Example response:

{
  "parsed": {
    "title": "Senior Product Manager",
    "company_name": "Acme Corp",
    "location": "Berlin, Germany",
    "work_mode": "hybrid",
    "salary_min": 80000,
    "salary_max": 100000,
    "salary_currency": "EUR",
    "salary_period": "yearly",
    "employment_type": "full-time",
    "ats_type": "greenhouse",
    "error": false,
    "error_reason": null,
    "description": "We're looking for a Senior Product Manager to…"
  },
  "parser_log_id": 4812
}

When parsing comes up empty: some boards can be reached but not read — the response then carries mostly null fields and an error_reason explaining why. no_title_extracted means Nico reached the posting but could not pull anything usable from it; in that case treat company_name as unreliable rather than as a finding, since it may have been derived from the domain.

Use job_application_parse_url before job_application_create to extract job details automatically — then pass the parsed data to the create tool.

You can pass a link forwarded by email. Gmail and Outlook rewrite links to their own redirect (google.com/url?q=…, Outlook SafeLinks); Nico unwraps those to the real posting URL, so a forwarded job parses and de-duplicates exactly as the original link would.

job_application_create

Add a job application to your board. It is created as a draft unless you pass status: "proposed", which marks it as a suggestion for the account owner to approve. Those are the only two values accepted — every later status is reached through job_application_transition, which is what records the change and keeps the history correct. The starting status no longer depends on who is calling. It previously became proposed automatically for anyone who wasn’t the account owner, which was invisible from the caller’s side. Parameters:

Parameter	Type	Required	Description
`title`	string	Yes	Job title
`company_name`	string	Yes	Company name (creates the company if it doesn’t exist)
`url`	string	No	Job posting URL
`location`	string	No	Job location
`work_mode`	string	No	One of: `remote`, `remote-optional`, `hybrid`, `on-site`
`status`	string	No	`draft` (default) or `proposed`

Idempotency: If this job is already tracked, the tool returns the existing application with "created": false rather than creating a duplicate. This is a success, not an error — the desired end state has been reached, so there’s nothing to retry. Every response carries created, and both cases return the same shape, so there is no need to call job_application_search first just to avoid a duplicate. Matching is on the canonical URL, so the same posting is recognised through a tracking parameter, a trailing slash, a differently-cased host, or an email-forward wrapper:

{
  "job_application": {
    "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
    "title": "Senior Product Manager",
    "url": "https://acme.com/careers/pm-senior",
    "status": "applied",
    "work_mode": "hybrid",
    "location": "Berlin, Germany",
    "company_name": "Acme Corp",
    "possible_transitions": ["acknowledge", "start_phone_screen", "start_interview", "reject", "withdraw"]
  },
  "created": false
}

Because the response carries status and possible_transitions, an agent that finds a job already tracked can act on it — advancing it with job_application_transition, say — without a follow-up read. Example response:

{
  "job_application": {
    "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
    "title": "Senior Product Manager",
    "url": "https://acme.com/careers/pm-senior",
    "status": "draft",
    "work_mode": "hybrid",
    "location": "Berlin, Germany",
    "company_name": "Acme Corp",
    "created_at": "2026-03-15T14:20:00Z"
  }
}

job_application_update

Correct the details of an existing application. Only the fields you pass are changed; everything else is left alone. Parameters:

Parameter	Type	Required	Description
`id`	string	Yes	The job application `id`
`title`	string	No	Job title
`url`	string	No	Job posting URL
`location`	string	No	Job location
`work_mode`	string	No	One of: `remote`, `remote-optional`, `hybrid`, `on-site`
`employment_type`	string	No	One of: `full-time`, `part-time`, `contract`, `internship`, `temporary`
`salary_min`	number	No	Lower bound of the salary range
`salary_max`	number	No	Upper bound of the salary range
`salary_currency`	string	No	ISO 4217 currency code, e.g. `EUR`
`salary_period`	string	No	One of: `hourly`, `daily`, `weekly`, `four_weekly`, `monthly`, `yearly`
`company_id`	string	No	Move the application to a different company, by that company’s `id`

status is not editable here. Use job_application_transition — a status change has to go through the application’s lifecycle so the history is recorded.

Example response:

{
  "job_application": {
    "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
    "title": "Staff Product Manager",
    "url": "https://acme.com/careers/pm-staff",
    "status": "applied",
    "work_mode": "hybrid",
    "location": "Berlin, Germany",
    "company_name": "Acme Corp",
    "possible_transitions": ["acknowledge", "start_phone_screen", "start_interview", "reject", "withdraw"]
  }
}

job_application_transition

Move an application to a new status by firing a lifecycle event. Which events are valid depends on where the application currently is — every response includes possible_transitions for exactly this reason. Parameters:

Parameter	Type	Required	Description
`id`	string	Yes	The job application `id`
`event`	string	Yes	The lifecycle event to fire (see below)
`comments`	string	No	Why the status changed — recorded on the history entry
`termination_reason`	string	No	Only meaningful with `reject` or `withdraw`; ignored otherwise

Events:

Event	Moves to	Notes
`apply`	`applied`	From `proposed` or `draft`
`acknowledge`	`acknowledged`	The company confirmed receipt
`start_phone_screen`	`phone_screen`
`start_interview`	`interviewing`
`advance_to_final_round`	`final_round`
`receive_offer`	`offer`
`start_negotiation`	`negotiating`
`accept_offer`	`hired`	Final
`reject`	`rejected`	Final — the company turned you down
`withdraw`	`withdrawn`	Final — you pulled out
`propose_to_draft`	`draft`
`move_back_to_applied`	`applied`	Correction
`move_back_to_acknowledged`	`acknowledged`	Correction
`move_back_to_phone_screen`	`phone_screen`	Correction
`move_back_to_interviewing`	`interviewing`	Correction
`move_back_to_offer`	`offer`	Correction

reject, withdraw and accept_offer are one-way. Nothing transitions out of rejected, withdrawn or hired — the move_back_to_* corrections do not reach them. Confirm with the account owner before firing one on their behalf.

Example response:

{
  "job_application": {
    "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
    "title": "Senior Product Manager",
    "url": "https://acme.com/careers/pm-senior",
    "status": "interviewing",
    "previous_status": "phone_screen",
    "work_mode": "hybrid",
    "location": "Berlin, Germany",
    "company_name": "Acme Corp",
    "possible_transitions": ["advance_to_final_round", "receive_offer", "reject", "withdraw", "move_back_to_applied", "move_back_to_acknowledged", "move_back_to_phone_screen"]
  }
}

When the event isn’t valid from the current status, the response names what is:

{
  "error": "Event 'accept_offer' cannot transition from 'draft'.",
  "current_status": "draft",
  "attempted_event": "accept_offer",
  "available_events": ["apply", "reject", "withdraw"]
}

job_application_add_note

Add a note to an existing job application. Notes are visible to all team members. Parameters:

Parameter	Type	Required	Description
`job_application_id`	string	Yes	The job application `id`
`body`	string	Yes	The note text (max 10,000 characters)

Example response:

{
  "note": {
    "id": "019e1e42-9abc-7000-9abc-5555cccc6666",
    "body": "Recruiter replied — call scheduled for Friday.",
    "author": "Alex",
    "job_application_id": "019e1e41-5678-7000-9abc-3333bbbb4444",
    "created_at": "2026-03-15T14:20:00Z"
  }
}

Interviews

Interviews belong to an application. Schedule them with job_application_add_interview, then read them back with interview_list — either for one application or across your whole account.

Times are ISO 8601. If you leave the UTC offset off — 2026-08-03T14:00 — Nico reads the time on your clock, using the timezone on your account. Include an offset when you want to be explicit.

Durations are whole minutes.

interview_list

List interviews, soonest first. Pass job_application_id to see one application’s interviews; leave it off for every interview on your account. Parameters:

Parameter	Type	Required	Description
`job_application_id`	string	No	Limit to one application’s interviews. Omit for all of them
`filter`	string	No	Time filter: `today`, `next_7_days`, `upcoming`, `past`. Omit for all interviews
`per_page`	integer	No	Results per page (default 25, max 100)
`page`	integer	No	Page number (default 1)

Example response:

{
  "interviews": [
    {
      "id": "019e1e43-1111-7000-9abc-7777dddd8888",
      "subject": "Technical interview with the platform team",
      "scheduled_at": "2026-08-03T14:00:00+02:00",
      "duration": 60,
      "ends_at": "2026-08-03T15:00:00+02:00",
      "upcoming": true,
      "interviewer": "Priya Raman, Engineering Manager",
      "location": null,
      "video_url": "https://meet.example.com/abc-defg-hij",
      "description": "Focus on system design.",
      "job_application": {
        "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
        "title": "Senior Product Manager",
        "company_name": "Acme Corp",
        "status": "interviewing"
      },
      "created_at": "2026-07-20T09:12:00Z",
      "updated_at": "2026-07-20T09:12:00Z"
    }
  ],
  "pagination": { "page": 1, "per_page": 25, "total_count": 1, "total_pages": 1 }
}

An unknown filter value is ignored rather than rejected — you get all interviews. Returns { "error": "Job application not found" } when job_application_id names an application that doesn’t exist or isn’t yours.

job_application_add_interview

Schedule an interview on an application. Parameters:

Parameter	Type	Required	Description
`job_application_id`	string	Yes	The job application `id`
`subject`	string	Yes	What the interview is about, e.g. `Technical interview with the platform team`
`scheduled_at`	string	Yes	When it takes place (ISO 8601, e.g. `2026-08-03T14:00:00+02:00`)
`duration`	integer	No	Length in minutes (default 60)
`interviewer`	string	No	Name(s) and role(s) of the interviewer(s)
`location`	string	No	Physical location, for in-person interviews
`video_url`	string	No	Video call link, for remote interviews
`description`	string	No	Preparation notes or other details

Example response:

{
  "interview": {
    "id": "019e1e43-1111-7000-9abc-7777dddd8888",
    "subject": "Technical interview with the platform team",
    "scheduled_at": "2026-08-03T14:00:00+02:00",
    "duration": 60,
    "ends_at": "2026-08-03T15:00:00+02:00",
    "upcoming": true,
    "interviewer": "Priya Raman, Engineering Manager",
    "location": null,
    "video_url": "https://meet.example.com/abc-defg-hij",
    "description": "Focus on system design.",
    "job_application": {
      "id": "019e1e41-5678-7000-9abc-3333bbbb4444",
      "title": "Senior Product Manager",
      "company_name": "Acme Corp",
      "status": "interviewing"
    },
    "created_at": "2026-07-20T09:12:00Z",
    "updated_at": "2026-07-20T09:12:00Z"
  }
}

Errors:

Response	Cause
`{ "error": "Job application not found" }`	Unknown `job_application_id`
`{ "error": "Invalid scheduled_at — use ISO 8601, e.g. 2026-08-03T14:00:00+02:00" }`	`scheduled_at` could not be read as a time
`{ "error": "Failed to create interview", "details": [...] }`	The interview was rejected — `details` says why

Adding an interview does not change the application’s status. Move it to interviewing yourself with job_application_transition.

interview_update

Reschedule or edit an existing interview. Only the fields you send are changed; everything else is left alone. Parameters:

Parameter	Type	Required	Description
`interview_id`	string	Yes	The interview `id`
`subject`	string	No	What the interview is about
`scheduled_at`	string	No	New time (ISO 8601, e.g. `2026-08-03T14:00:00+02:00`)
`duration`	integer	No	Length in minutes
`interviewer`	string	No	Name(s) and role(s) of the interviewer(s)
`location`	string	No	Physical location, for in-person interviews
`video_url`	string	No	Video call link, for remote interviews
`description`	string	No	Preparation notes or other details

Send at least one field besides interview_id. The response is the same shape as job_application_add_interview, with the updated values. Errors:

Response	Cause
`{ "error": "Interview not found" }`	Unknown `interview_id`
`{ "error": "No updatable fields given. Provide at least one of: ..." }`	Only `interview_id` was sent
`{ "error": "Invalid scheduled_at — use ISO 8601, e.g. 2026-08-03T14:00:00+02:00" }`	`scheduled_at` could not be read as a time
`{ "error": "Failed to update interview", "details": [...] }`	The change was rejected — `details` says why

Overview

AI Agents

Authentication

External Tools

MCP Server

MCP Server

What can the MCP server do?

Connecting your AI assistant

Claude (Desktop and claude.ai)

ChatGPT

Job posting search

job_posting_search

job_posting_get

Job application management

job_application_search

job_application_list

job_application_get

job_application_parse_url

job_application_create

job_application_update

job_application_transition

job_application_add_note

Interviews

interview_list

job_application_add_interview

interview_update

​MCP Server

​What can the MCP server do?

​Connecting your AI assistant

​Claude (Desktop and claude.ai)

​ChatGPT

​Job posting search

​job_posting_search

​job_posting_get

​Job application management

​job_application_search

​job_application_list

​job_application_get

​job_application_parse_url

​job_application_create

​job_application_update

​job_application_transition

​job_application_add_note

​Interviews

​interview_list

​job_application_add_interview

​interview_update

MCP Server

What can the MCP server do?

Connecting your AI assistant

Claude (Desktop and claude.ai)

ChatGPT

Job posting search

job_posting_search

job_posting_get

Job application management

job_application_search

job_application_list

job_application_get

job_application_parse_url

job_application_create

job_application_update

job_application_transition

job_application_add_note

Interviews

interview_list

job_application_add_interview

interview_update