# GigHQ.ai (remote · mcp.gighq.ai)

Job-search tracker for AI agents: applications, stale follow-ups, skills gaps, H-1B lookup.

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.gighq.ai`: 82/100 (this document), [markdown](https://verifymcp.io/servers/ai-gighq-gighq/mcp.md), [page](https://verifymcp.io/servers/ai-gighq-gighq/mcp)

## Channel facts

- Endpoint: `https://mcp.gighq.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 7189 tokens (~211/item across 34 items; 34 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 35 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the GigHQ.ai MCP server?

GigHQ.ai is a hosted endpoint at https://mcp.gighq.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-gighq-gighq 'https://mcp.gighq.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-gighq-gighq": {
      "url": "https://mcp.gighq.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-gighq-gighq": {
      "type": "http",
      "url": "https://mcp.gighq.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-gighq-gighq]
url = "https://mcp.gighq.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-gighq-gighq": {
      "type": "remote",
      "url": "https://mcp.gighq.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-gighq-gighq --url 'https://mcp.gighq.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-gighq-gighq:
    url: "https://mcp.gighq.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-gighq-gighq": {
      "Transport": "http",
      "Url": "https://mcp.gighq.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-gighq-gighq -t streamable-http -u 'https://mcp.gighq.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-gighq-gighq": {
      "type": "http",
      "url": "https://mcp.gighq.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 82, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-04 (score 81, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-03 (score 81, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-02 (score 80, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-01 (score 80, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-31 (score 80, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-30 (score 79, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-29 (score 79, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

## MCP tools (34)

### `search_companies` (~44 tokens)

Search for companies by name to retrieve their unique identifiers (UUIDs).

Input parameters:

- `name` (string, required): The name of the company to search for (e.g., 'Human')

Output parameters:

- `count` (number)
- `results` (array)

### `get_company_details` (~236 tokens)

Get detailed information about a company (applicants by status, Community Signal, H1B sponsorship status, employee count, website, etc.) using its UUID.

The metrics window defaults to the last 30 days. Optional startDate and endDate parameters support other date ranges. Returns GigHQ's recorded company data and community metrics for the selected window.

Input parameters:

- `companyId` (string, required): The UUID for the company (obtain from search_companies), or a plain company name — the tool will auto-resolve a name to a UUID if a valid UUID is not provided.
- `endDate` (string): End of the metrics window in ISO 8601 format. Defaults to today if omitted.
- `startDate` (string): Start of the metrics window in ISO 8601 format (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS). Compute this from natural-language ranges: 'last 6 months' → today minus 6 months, 'last year' → today minus 12 mon…

Output parameters:

- `data` (object)

### `get_job_details` (~203 tokens)

Get detailed community metrics for a specific job listing (applicants by status, average days per status, Community Signal) using its UUID.

The metrics window defaults to the last 30 days. When the user requests a longer period — e.g. "last 6 months", "last year", "since January" — compute startDate and endDate from that phrase and pass them explicitly.

Input parameters:

- `endDate` (string): End of the metrics window in ISO 8601 format. Defaults to today if omitted.
- `jobId` (string, required): The unique identifier (UUID) for the job listing.
- `startDate` (string): Start of the metrics window in ISO 8601 format (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS). Compute from natural-language ranges: 'last 6 months' → today minus 6 months, 'last year' → today minus 12 months.…

Output parameters:

- `data` (object)

### `update_job_application_status` (~331 tokens)

STOP — if the user says "not interested", "no longer interested", "withdraw interest", "remove from pipeline", or any equivalent: do NOT call this tool. Call toggle_job_application_interest instead. There is no "not interested" status here; attempting to use REJECTED or any other status as a proxy is wrong.

Updates the status of a job application by its UUID to one of the supported pipeline stages.

Status meanings:
\- REJECTED: the company rejected the candidate (recorded internally as company-rejected)
\- For candidate withdrawal use toggle_job_application_interest instead

Allowed transitions (invalid transitions are silently ignored by the API — validate before calling):
\- PROSPECTING  → PROSPECTING, APPLIED, INTERVIEWING, OFFER, REJECTED, PENDING
\- APPLIED      → APPLIED, PENDING, INTERVIEWING, OFFER, REJECTED
\- INTERVIEWING → INTERVIEWING, PENDING, OFFER, REJECTED
\- OFFER        → OFFER, REJECTED, PENDING
\- REJECTED     → REJECTED, PENDING, APPLIED
\- PENDING      → APPLIED, INTERVIEWING, OFFER, REJECTED
\- UNKNOWN      → (nothing — all transitions blocked)

Input parameters:

- `currentStatus` (string, required): The current status of the job application (required to validate the transition).
- `status` (string, required): The new status for the job application.
- `uuid` (string, required): The UUID of the job application to update (the 'uuid' field, not the numeric 'id').

Output parameters:

- `message` (string)
- `result`

### `toggle_job_application_interest` (~293 tokens)

Use this tool when the user says "not interested", "no longer interested", "withdraw interest", "I'm out", "remove from pipeline", or any equivalent phrase. This is the ONLY correct tool for withdrawing interest — do not use update_job_application_status as a proxy.

Deactivates an active application (or reactivates a previously deactivated one). Mirrors the "I am no longer interested in this role" button in the GigHQ app.

Pass `currentIsActive: true` to deactivate an active application:
\- Stamps an end date on the current status stage (appliedEndDate, interviewingEndDate, or offerEndDate)
\- Sets status to CANDIDATE_WITHDREW and sets endDate = now

Pass `currentIsActive: false` to reactivate a previously deactivated application:
\- Clears endDate and resets status to APPLIED

Check the current `isActive` value with get_job_application or search_job_applications before calling.

Input parameters:

- `currentIsActive` (boolean, required): The current active state of the application. Pass true if the application is currently active (this will deactivate it); pass false if it is currently inactive (this will reactivate it). Retrieve thi…
- `uuid` (string, required): The UUID of the job application to update (the 'uuid' field, not the numeric 'id').

Output parameters:

- `message` (string)
- `result`

### `get_recent_applications` (~77 tokens)

Retrieves a summary of the user's 10 most recent job applications, including status, company name, and correspondence dates. `totalCount` in the response reflects the full number of applications, not just the 10 returned — mention it if it's larger than the list shown, and point the user to search_job_applications for the rest.

Output parameters:

- `applications`
- `assignedEmails` (array)
- `dashboardUrl` (string)
- `tips` (array)
- `totalCount` (number)

### `search_job_applications` (~302 tokens)

Search the user's job applications by company name, status, or both. Use this when the user asks about a specific company's application, wants to find a particular application to view or update its status, or wants to know how many applications are in a given status (e.g. "how many applications are in Prospecting?").

Omit `company` to search across all companies — required when the request is status-only.

Returns matching applications with their UUIDs — the UUID is what feeds into update_job_application_status and toggle_job_application_interest. `totalCount` in the response reflects the full match count, not just the page returned (see `take`/`skip`).

Matching is case-insensitive and substring-based: "stripe" matches "Stripe", "Stripe Inc", etc.
If the user applied to the same company more than once (e.g., different roles), all matches are returned; use jobTitle and correspondenceDate to disambiguate.

Input parameters:

- `company` (string): Company name to search for. Case-insensitive substring match. Omit to search across all companies.
- `isActive` (boolean): Default true (active applications only). Pass false to search applications marked 'no longer interested'.
- `skip` (integer): Offset for pagination (default 0).
- `status` (string): Optional: filter results to a specific application status.
- `take` (integer): Max results to return (default 20, max 50).

Output parameters:

- `results`
- `totalCount` (number)

### `get_job_application` (~118 tokens)

Fetches the full details of a single job application by its UUID — status history, correspondence dates, job description, and related metadata.

Do NOT use this tool when the user asks about notes ("do I have any notes", "show me my notes", "list notes"). Use list_job_application_notes for that.

Tip: if you only have a company name, call search_job_applications first to get the UUID.

Input parameters:

- `uuid` (string, required): The UUID of the job application (the 'uuid' field, not the numeric 'id').

Output parameters:

- `aiSummary` (string|null)
- `appUrl` (string)
- `application`

### `create_job_application` (~273 tokens)

Creates a new job application entry in GigHQ, or reuses an existing active one for the same company+job if the backend finds one — check `alreadyExist` in the response. Calling find_job_application first is still recommended when you want to inspect a possible match before deciding.

New applications always start in PROSPECTING status — there is no way to create directly into APPLIED/INTERVIEWING/etc. If the user has already applied, call update_job_application_status with status "APPLIED" right after this returns.

Optionally pass `source_url` and/or `job_description` to save them in the same call — attached best-effort after the application is created/found. If that secondary save fails, the create/find itself still succeeds and a warning is included in the response instead of an error.
When an existing application is reused, supplied posting details can replace its saved source URL or job description.

Input parameters:

- `company` (string, required): The name of the company you applied to.
- `job` (string, required): The job title or role you applied for.
- `job_description` (string): The full job description text, if known. Saved best-effort after create/find.
- `source_url` (string): The URL of the job posting, if known. Saved best-effort after create/find.

Output parameters:

- `alreadyExist` (boolean)
- `appUrl` (string)
- `application`
- `uuid` (string)
- `warnings` (array)

### `find_job_application` (~223 tokens)

Checks whether the user already has a saved job application for a SPECIFIC posting — call this before create_job_application to avoid creating a duplicate. Matches BOTH company name and job title (case-insensitive substring on each), so it can tell two different roles at the same company apart. search_job_applications cannot do this — it only filters by company/status/isActive, not job title.

Both `company` and `job` are required.

Scope limitation: matches are restricted server-side to APPLIED, INTERVIEWING, and PROSPECTING status. An application the user marked REJECTED/OFFER, or withdrew interest in, will NOT appear here even if the title/company match.

If `found` is false, it's safe to call create_job_application. If true, prefer reusing the existing UUID (e.g. via update_job_application or add_job_application_note) instead of creating a duplicate.

Input parameters:

- `company` (string, required): Company name to match (case-insensitive substring).
- `job` (string, required): Job title to match (case-insensitive substring).

Output parameters:

- `count` (integer)
- `found` (boolean)
- `matches` (array)

### `update_job_application` (~207 tokens)

Enriches or corrects an existing job application's saved posting details: source URL and/or job description. Use this when the user finds the JD later, wants to add the posting link, or wants to correct the saved description.

Do NOT use this for status changes — use update_job_application_status. Do NOT use this for withdraw/reactivate ('not interested') — use toggle_job_application_interest. This tool only touches source_url and job_description.

At least one of source_url or job_description is required. job_description REPLACES the previously saved description — pass the full text, not a diff. Omitting a field leaves it unchanged.

Input parameters:

- `job_description` (string): The full job description text. Replaces any previously saved description for this application.
- `source_url` (string): The URL of the job posting.
- `uuid` (string, required): The UUID of the job application to update. Find it with search_job_applications, find_job_application, or get_recent_applications.

Output parameters:

- `appUrl` (string)
- `message` (string)
- `updatedFields` (array)
- `uuid` (string)

### `lookup_h1b_sponsorship` (~76 tokens)

Looks up a company by name and returns GigHQ's recorded H1B sponsorship and concurrent H1B flags. Returns unknown when a flag is unavailable. These results describe the data recorded in GigHQ.

Input parameters:

- `company_name` (string, required): The name of the company to look up (e.g., 'Google').

Output parameters:

- `company` (string)
- `h1b_sponsor` (boolean|null)
- `supports_h1b_transfers` (boolean|null)
- `uuid` (string)

### `check_stale_applications` (~74 tokens)

Returns job applications that haven't had a status update in a configurable number of days, along with a suggested follow-up action for each. Useful for surfacing applications the user may have forgotten about.

Input parameters:

- `days` (integer): Number of days without a status change before an application is considered stale. Defaults to 14.

Output parameters:

- `applications` (array)
- `dashboardUrl` (string)
- `staleCount` (integer)
- `thresholdDays` (integer)

### `weekly_job_search_summary` (~52 tokens)

Generates a weekly job search health summary. Aggregates up to 30 active applications and surfaces status distribution, conversion rates, longest-open applications, pipeline clustering insights, and a suggested focus area for the coming week.

Output parameters:

- `dashboardUrl` (string)
- `summary`

### `get_job_fit_evidence` (~171 tokens)

Retrieves a saved GigHQ job application, candidate profile data, and the most relevant Career Journal evidence for assessing role fit. Career evidence is ranked by job keywords, competency coverage, evidence quality, recency, and diversity; the default is 20 entries, grouped by competency bucket (career_journal.competency_rollup) to make coverage and gaps easy to spot. This read-only tool supplies evidence and retrieval metadata only. It does not assess the candidate, calculate a fit score, or modify records. If the job description is missing, it returns the application link and a substantive/recent evidence fallback.

Input parameters:

- `application_uuid` (string, required): UUID of the saved GigHQ job application.
- `career_entry_limit` (integer): Maximum Career Journal entries to return (default 20, max 50).

Output parameters:

- `application`
- `candidate`
- `career_journal`
- `fallback_guidance` (string)
- `missing_context` (array)
- `provenance`
- `purpose` (string)

### `prepare_for_interview` (~138 tokens)

Assembles everything needed to prepare for an interview on a saved GigHQ job application: the job and company context, the candidate's full profile, their Career Journal grouped by role (for STAR/CAR story material), which evidence best matches the role (to emphasize) and which competencies are weakly covered (to address or reframe), and a company briefing (Community Signal, H1B status, size). This read-only tool supplies context only — it does not generate interview questions, write STAR/CAR answers, or assess the candidate.

Input parameters:

- `application_uuid` (string, required): UUID of the saved GigHQ job application to prepare for.

Output parameters:

- `application`
- `candidate`
- `career_journal`
- `company_context`
- `fallback_guidance` (string)
- `fit_signal`
- `missing_context` (array)
- `provenance`
- `purpose` (string)

### `add_career_entry` (~795 tokens)

Saves a new career journal entry to the user's GigHQ profile. Use this to document professional achievements, projects, skills acquired, or reflections tied to a specific role.

Entry types:
  1 = achievement — a concrete win, result, or impact (default)
  2 = project — a specific initiative the user owned or contributed to
  3 = skill_acquired — a new skill, tool, or capability gained
  4 = reflection — a lesson learned or professional observation

Tip: if the user hasn't specified a role, call `list_experiences` first, present the options, and ask which role this entry belongs to. Then pass the confirmed integer ID as `experience_id`.
experience_id is optional — entries without one are valid but less useful for resume generation and interview prep, since they can't be linked to a specific role.

STAR structure (achievement entries): walk the user through their story in order, one piece at a time — don't interrogate with a checklist —
  Situation: the context or challenge beforehand
  Task: what specifically needed to be done or the goal to achieve
  Action: the concrete steps actually taken
  Result: the outcome, ideally with (1) scale of action: how much, how many, what scope (team size, users, codebase size, budget, requests/sec, etc.), (2) direct result: the measurable outcome (latency reduced by X%, errors down by Y, shipped Z weeks ahead of schedule), and (3) organizational impact: what that result meant for the business, team, or users (saved $X, unblocked N engineers, contributed to Y% revenue growth)
Write `description` as a clearly labeled STAR narrative — "Situation: ... Task: ... Action: ... Result: ..." — rather than one unstructured paragraph.
Before calling this tool for an achievement entry, confirm you have all four STAR parts from the user. If the Result's numbers are genuinely unavailable, note that in the description and ask the user to follow up later via update_career_entry.
Project entries benefit from the same Result-quantification numbers…

Input parameters:

- `description` (string, required): Full narrative in the user's own words. For achievement entries, write it as a labeled STAR narrative — "Situation: ... Task: ... Action: ... Result: ..." — not one unstructured paragraph. For other…
- `entry_date` (string): ISO 8601 date when this happened, e.g. '2024-03-15'. Defaults to today if omitted.
- `experience_id` (integer): Integer ID of the GigHQ experience record (role) this entry belongs to. Use list_career_entries or the gighq://experience resource to find the ID.
- `metrics` (string): Three-number quantification: (1) scale of action, (2) direct result, (3) organizational impact. E.g. 'Serving 50k daily users [scale] — reduced checkout latency from 2.1s to 0.4s [result] — increased…
- `tags` (string): Comma-separated skill or topic tags, e.g. 'TypeScript, system design, stakeholder management'.
- `title` (string, required): Short headline summarising the entry (e.g. 'Led migration of payments service to microservices').
- `type` (integer): Entry type: 1=achievement, 2=project, 3=skill_acquired, 4=reflection. Pass an integer or the label string. Defaults to 1.

Output parameters:

- `entry`
- `message` (string)
- `profileUrl` (string)
- `updatedFields` (array)
- `uuid` (string)

### `update_career_entry` (~279 tokens)

Updates an existing career journal entry. Only the fields provided will be changed — all other fields remain as-is. Use this to refine descriptions, add missing numbers to the metrics field, correct the entry date, or re-type an entry. This is the right tool to backfill quantification on entries saved without a full three-number breakdown (scale of action, direct result, organizational impact).

Input parameters:

- `description` (string): Updated narrative text.
- `entry_date` (string): Updated ISO 8601 date, e.g. '2024-06-01'.
- `experience_id` (integer): Updated experience (role) ID to attach this entry to.
- `metrics` (string): Updated quantifiable impact using the three-number rule: (1) scale of action, (2) direct result, (3) organizational impact. Use this to backfill missing numbers on entries that were saved without the…
- `tags` (string): Updated comma-separated tags.
- `title` (string): Updated headline for the entry.
- `type` (integer): Updated type: 1=achievement, 2=project, 3=skill_acquired, 4=reflection. Pass an integer or the label string.
- `uuid` (string, required): UUID of the career entry to update. Returned by add_career_entry or list_career_entries.

Output parameters:

- `entry`
- `message` (string)
- `profileUrl` (string)
- `updatedFields` (array)
- `uuid` (string)

### `list_career_entries` (~250 tokens)

Returns the user's career journal entries from GigHQ, newest first. Supports optional filtering by entry type and date range.

Use this tool to:
  \- Review what the user has already documented before starting a journaling session
  \- Find entries to update or refine
  \- Identify gaps (roles with few or no entries)
  \- Synthesise entries into resume bullets or interview stories

Entry type filter values: 1=achievement, 2=project, 3=skill_acquired, 4=reflection.

Input parameters:

- `end_date` (string): ISO 8601 end date to filter entries on or before, e.g. '2024-12-31'.
- `skip` (integer): Number of entries to skip for pagination.
- `start_date` (string): ISO 8601 start date to filter entries on or after, e.g. '2024-01-01'.
- `take` (integer): Number of entries to return (default 25, max 100).
- `type` (integer): Filter by entry type: 1=achievement, 2=project, 3=skill_acquired, 4=reflection. Omit for all types.

Output parameters:

- `entries` (array)
- `profileUrl` (string)
- `returned` (integer)
- `total` (integer)

### `delete_career_entry` (~74 tokens)

Permanently deletes a career journal entry by UUID. This action cannot be undone — confirm with the user before calling. Use list_career_entries to find the UUID if you don't have it.

Input parameters:

- `uuid` (string, required): UUID of the career entry to delete. Returned by add_career_entry or list_career_entries.

Output parameters:

- `entry`
- `message` (string)
- `profileUrl` (string)
- `updatedFields` (array)
- `uuid` (string)

### `get_career_journal_prompts` (~165 tokens)

Returns a set of context-aware reflection questions to guide a career journaling session. Use this at the start of any journaling conversation to orient the discussion.

The tool reads the user's GigHQ experience records and existing career entries to tailor the questions — surfacing the most relevant role, estimating tenure, and flagging roles with sparse documentation.

Session types:
  achievement — document a specific win or impact
  quarterly   — end-of-quarter reflection (default)
  onboarding  — first 90 days at a new role
  wrap-up     — leaving a role or wrapping up an internship
  job-search  — actively applying; synthesise story and close gaps

Input parameters:

- `session_type` (string): Type of journaling session. Defaults to 'quarterly'.

Output parameters:

- `gap_note` (string)
- `guided_questions` (array)
- `instruction` (string)
- `onboarding_note` (string)
- `profile_url` (string)
- `session_type` (string)
- `user_context`

### `list_experiences` (~99 tokens)

Returns the user's work experience records with their integer IDs.

Use this tool BEFORE calling `add_career_entry` or `update_career_entry` to find the
correct `experience_id` for the role the entry belongs to. Present the role list to
the user and confirm which one they mean before saving.

This is the tool-based alternative to the `gighq://experience` resource and works in
all contexts including voice mode.

Output parameters:

- `experiences` (array)

### `add_job_application_note` (~327 tokens)

Adds a note to a job application's timeline. Use this to log any touchpoint or interaction — a call, a LinkedIn message, a referral conversation, a networking event, etc.

\**category is required.** Infer the best-fit category from the note content before calling. Use this mapping:
  • text_message — contact via SMS/text
  • email_external — contact via email
  • call — phone or video call
  • linkedin_connection_request — sent or received a LinkedIn connection request
  • linkedin_message — direct message on LinkedIn
  • coffee_chat — informational interview or coffee chat
  • in_person_meeting — face-to-face meeting
  • networking_event — conference, meetup, career fair, or similar event
  • referral — someone referred the user or made an introduction
  • other — genuinely doesn't fit any of the above

If the category is still ambiguous after reading the note, present the options to the user and ask them to confirm before calling this tool.
The application_id is the UUID of the job application — use get_recent_applications or search_job_applications to find it.

Input parameters:

- `application_id` (string, required): UUID of the job application to attach this note to.
- `body` (string, required): The note text (plain text or Markdown). Max 3000 characters.
- `category` (string, required): Category tag for the note. Use a slug from the tool description (e.g. 'call', 'in_person_meeting'). Display labels like 'Call' or 'In-Person Meeting' are also accepted.

Output parameters:

- `appUrl` (string)
- `message` (string)
- `uuid` (string)

### `list_job_application_notes` (~107 tokens)

Use this tool when the user asks about notes on a job application — "do I have any notes", "show me my notes", "what notes do I have", etc. Returns all user-authored notes for a job application ordered by date, including UUID, body text, category, and timestamp. Use the returned UUIDs in follow-up update_job_application_note or delete_job_application_note calls.

Input parameters:

- `application_id` (string, required): UUID of the job application whose notes to retrieve.

Output parameters:

- `appUrl` (string)
- `application_id` (string)
- `count` (integer)
- `notes` (array)

### `update_job_application_note` (~318 tokens)

Updates the body or category of an existing job application note. Both body and category are required — the backend replaces the full note on update.

If the user only mentions updating the body and doesn't specify a category, infer the best-fit category from the note content using this mapping:
  • text_message — contact via SMS/text
  • email_external — contact via email
  • call — phone or video call
  • linkedin_connection_request — sent or received a LinkedIn connection request
  • linkedin_message — direct message on LinkedIn
  • coffee_chat — informational interview or coffee chat
  • in_person_meeting — face-to-face meeting
  • networking_event — conference, meetup, career fair, or similar event
  • referral — someone referred the user or made an introduction
  • other — genuinely doesn't fit any of the above

If ambiguous, ask the user to confirm before calling. Use list_job_application_notes to retrieve the note UUID if you don't have it.

Input parameters:

- `application_id` (string, required): UUID of the job application this note belongs to.
- `body` (string, required): Updated note text. Max 3000 characters.
- `category` (string, required): Category tag for the note. Use a slug from the tool description (e.g. 'call', 'in_person_meeting'). Display labels like 'Call' or 'In-Person Meeting' are also accepted.
- `note_uuid` (string, required): UUID of the note to update. Returned by add_job_application_note or list_job_application_notes.

Output parameters:

- `appUrl` (string)
- `message` (string)
- `uuid` (string)

### `delete_job_application_note` (~93 tokens)

Permanently deletes a note from a job application's timeline. This action cannot be undone — confirm with the user before calling. Use list_job_application_notes to find the note UUID if you don't have it.

Input parameters:

- `application_id` (string, required): UUID of the job application this note belongs to.
- `note_uuid` (string, required): UUID of the note to delete. Returned by add_job_application_note or list_job_application_notes.

Output parameters:

- `appUrl` (string)
- `message` (string)
- `uuid` (string)

### `search_contacts` (~188 tokens)

Searches the user's job-search contacts in GigHQ — recruiters, hiring managers, referrals, and other people they are networking with.

Use this tool to:
  \- Find a contact before drafting an outreach or follow-up message
  \- See who the user already knows at a company before an interview or application
  \- Review which contacts are stuck at a given outreach stage

Status filter values: not_contacted, reached_out, responded, in_conversation, connected, cold.
Contacts are created in the GigHQ app or via the browser extension — this MCP connection cannot create or delete them.

Input parameters:

- `name` (string): Filter by contact name (case-insensitive substring match).
- `skip` (integer): Number of contacts to skip for pagination.
- `status` (string): Filter by outreach status.
- `take` (integer): Number of contacts to return (default 25, max 100).

Output parameters:

- `contacts` (array)
- `contactsUrl` (string)
- `returned` (integer)
- `total` (integer)

### `get_contact` (~100 tokens)

Returns full details for one of the user's job-search contacts: profile info, outreach status, linked job applications, and the complete interaction history (calls, LinkedIn messages, coffee chats, etc.).

Use this before drafting outreach or follow-up messages so the message reflects what has already been said, and before interviews to remind the user who they know at the company.
Find the UUID with `search_contacts`.

Input parameters:

- `contact_id` (string, required): UUID of the contact.

Output parameters:

- `contact` (object)
- `contactUrl` (string)

### `update_contact_status` (~94 tokens)

Updates a contact's outreach status in GigHQ. A status-change entry is automatically logged in the contact's interaction history.

Status progression: not_contacted → reached_out → responded → in_conversation → connected. Use 'cold' when the thread has gone quiet.
Find the contact's UUID with `search_contacts`.

Input parameters:

- `contact_id` (string, required): UUID of the contact.
- `status` (string, required): New outreach status.

Output parameters:

- `contactUrl` (string)
- `message` (string)
- `uuid` (string)

### `add_contact_interaction` (~262 tokens)

Logs a touchpoint with one of the user's job-search contacts — a call, a LinkedIn message, a coffee chat, a referral conversation, etc. The entry appears in the contact's interaction timeline in GigHQ.

\**type is required.** Infer the best-fit type from what happened:
  • text_message — SMS/text
  • email_external — email
  • call — phone or video call
  • linkedin_connection_request — sent or accepted a connection request
  • linkedin_message — direct message on LinkedIn
  • coffee_chat — informational interview or coffee chat
  • in_person_meeting — face-to-face meeting
  • networking_event — conference, meetup, career fair
  • referral — the contact referred the user or made an introduction
  • other — anything else

Find the contact's UUID with `search_contacts`.

Input parameters:

- `body` (string, required): Short note about the interaction — what was discussed or sent. Max 3000 characters.
- `contact_id` (string, required): UUID of the contact.
- `occurred_at` (string): ISO 8601 date the interaction happened, e.g. '2026-07-10'. Defaults to now.
- `type` (string, required): Kind of interaction being logged.

Output parameters:

- `contactUrl` (string)
- `message` (string)
- `uuid` (string)

### `get_career_compass` (~71 tokens)

Retrieves the user's saved CareerCompass data: professional objectives, positioning statement, categorized skills (technical/soft/management/other), and target market (industries, company size, geographic location). Cheap read — prefer this over generate_career_compass whenever the user just wants to review what's already saved.

Output parameters:

- `career_stage` (string|null)
- `career_switch_type` (string|null)
- `company_size` (array)
- `geographic_location` (array)
- `is_saved` (boolean)
- `management_skills` (array)
- `objective_suggestions` (array)
- `other_skills` (array)
- `positioning_statement` (string|null)
- `professional_objectives` (string|null)
- `soft_skills` (array)
- `target_industries` (array)
- `target_industry` (string|null)
- `target_job_titles` (array)
- `target_role` (string|null)
- `technical_skills` (array)

### `generate_career_compass` (~171 tokens)

Runs GigHQ's CareerCompass AI pipeline against the user's resume data to generate 3 candidate professional objective statements, a positioning statement, categorized skills, and a suggested target market (industries, company sizes, geographic locations). This is an EXPENSIVE, one-time 'career strategy' action (4 parallel AI completions server-side) — not a cheap or repeatable lookup. Prefer get_career_compass first to check for existing saved data. Nothing is persisted by this call; use save_career_compass afterward, and only with the user's explicit review and authorization.

Input parameters:

- `career_stage` (string): The user's career stage, if known. Omit if not established in the conversation.
- `career_switch_details` (object): Required for useful output when career_stage is 'Career Switcher'.

Output parameters:

- `objective_suggestions` (array)
- `objectives` (array)
- `positioning_statement` (string)
- `purpose` (string)
- `skills`
- `target_market`

### `save_career_compass` (~432 tokens)

Persists CareerCompass data to the user's GigHQ profile. This REPLACES the full saved record — any array field you omit (technical_skills, soft_skills, management_skills, target_industries, company_size, geographic_location, other_skills) is saved as empty, not left unchanged. Call get_career_compass first and pass through every field the user isn't changing. Only call this after the user has reviewed the content (e.g. from generate_career_compass) and explicitly authorized saving it.

Input parameters:

- `career_stage` (string)
- `career_switch_type` (string)
- `company_size` (array): Target company sizes. Omitting this clears any previously saved company sizes.
- `geographic_location` (array): Target geographic locations. Omitting this clears any previously saved locations.
- `is_complete` (boolean): Defaults to true server-side. Pass false only for an explicit partial/in-progress save.
- `management_skills` (array): Management skills. Omitting this clears any previously saved management skills.
- `objective_suggestions` (array): The AI-generated objective candidates shown to the user, so a resumed session can show the same options.
- `other_skills` (array): Other skills. Omitting this clears any previously saved other skills.
- `positioning_statement` (string): The chosen positioning statement.
- `professional_objectives` (string): The chosen professional objective statement.
- `progress_step` (integer): Wizard step reached, for an in-progress save (is_complete: false).
- `soft_skills` (array): Soft skills. Omitting this clears any previously saved soft skills.
- `target_industries` (array): Target industries. Omitting this clears any previously saved target industries.
- `target_industry` (string): Single primary target industry, distinct from the target_industries list.
- `target_job_titles` (array): Up to 5 target job titles.
- `target_role` (string): Single primary target role.
- `technical_skills` (array): Technical skills. Omitting this clears any previously saved technical skills.

Output parameters:

- `message` (string)
- `profileUrl` (string)

### `recommend_target_roles` (~200 tokens)

Assembles the user's profile, experience, career journal evidence (with a broad competency rollup), and saved CareerCompass data (if any) for recommending role titles to target. This is the inverse of get_job_fit_evidence: instead of evaluating fit for one specific job, it starts from the candidate's profile. Role taxonomy only — it does NOT validate recommendations against live job-market demand or hiring volume; that is future work. This read-only tool assembles context only; the client model produces the tiered (Strong fit / Stretch / Not recommended) recommendation.

Input parameters:

- `industry_preference` (string): Industry the user wants to target, if stated.
- `location_preference` (string): Remote/hybrid/location preference, if stated.
- `open_to_pivot` (boolean): Whether the user is open to a role/industry pivot, if stated.
- `seniority` (string): Seniority level the user is targeting, if stated.

Output parameters:

- `candidate`
- `career_compass`
- `competency_rollup`
- `missing_context` (array)
- `provenance`
- `purpose` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-gighq-gighq/mcp#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 80
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 79
- 2026-10-29: 79
- 2026-10-28: 78
- 2026-10-27: 78
- 2026-10-26: 77
- 2026-10-25: 77
- 2026-10-24: 76
- 2026-10-23: 76

## Common questions

### What is the GigHQ.ai MCP server?

GigHQ.ai is an MCP server listed in the public MCP registry as ai.gighq/gighq. Job-search tracker for AI agents: applications, stale follow-ups, skills gaps, H-1B lookup. This page covers its hosted endpoint (https://mcp.gighq.ai/mcp).

### Is the GigHQ.ai MCP server safe to use?

GigHQ.ai scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the GigHQ.ai MCP server expose?

GigHQ.ai exposes 34 tools: search_companies, get_company_details, get_job_details, update_job_application_status, toggle_job_application_interest, and 29 more. Their descriptions and schemas cost roughly 6,843 tokens of context every time the server is loaded.

### Does the GigHQ.ai MCP server require authentication?

Yes. GigHQ.ai asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the GigHQ.ai MCP server still maintained?

GigHQ.ai is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the GigHQ.ai MCP server?

VerifyMCP ran 13 checks on GigHQ.ai, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.gighq.ai/mcp
- Repository: https://github.com/gighq-ai/gighq-skill
- Website: https://www.gighq.ai/mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/ai-gighq-gighq/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-gighq-gighq/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-gighq-gighq/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-gighq-gighq/mcp