# Jobero job search (remote · jobero.ai)

Paid job search: 7 matched roles, each with a tailored CV and cover letter.

- Trust score: 59/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `jobero.ai`: 59/100 (this document), [markdown](https://verifymcp.io/servers/ai-jobero-job-search/jobero.md), [page](https://verifymcp.io/servers/ai-jobero-job-search/jobero)

## Channel facts

- Endpoint: `https://jobero.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- 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 2026-08-03.

- **Endpoint Security**: 49/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 869 tokens (~173/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http ai-jobero-job-search https://jobero.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-jobero-job-search]
url = "https://jobero.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-jobero-job-search --url https://jobero.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-jobero-job-search:
    url: "https://jobero.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-jobero-job-search": {
      "type": "http",
      "url": "https://jobero.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.

### 2026-08-03 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 58, +3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “start_job_search” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 67% → 100%
- [functional improvement] Tool “get_pricing” now declares an output schema
- [functional improvement] Tool “get_search_status” now declares an output schema
- [functional improvement] Tool “register_agent” now declares an output schema
- [functional improvement] Tool “start_job_search” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: fair → good
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “quick_job_search”
- [cosmetic] “start_job_search” added an optional parameter “cv_json”
- [cosmetic] “get_search_status” reworded the description of “run_id”
- [cosmetic] “register_agent” reworded the description of “email”
- [cosmetic] “register_agent” reworded the description of “name”
- [cosmetic] “start_job_search” reworded the description of “cv_base64”
- [cosmetic] “start_job_search” reworded the description of “cv_type”
- [cosmetic] “start_job_search” reworded the description of “profile”
- [cosmetic] “start_job_search” made “cv_base64” optional

### 2026-08-01 (score 55, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-31 (score 55)

First indexed and scored.

## MCP tools (5)

### `get_pricing` (~33 tokens)

Get pricing

What a Jobero search costs and how to pay for it, in card and stablecoin terms. No auth required.

Output parameters:

- `card_checkout` (string): URL for card payment
- `credits_are_per_product` (boolean): Always true: a quick credit cannot pay for a full search
- `free_searches` (boolean): Always false: registration grants no credits
- `packs` (array): Buyable credit packs
- `products` (array): The two things Jobero sells
- `service` (string): Service name
- `x402`: Stablecoin payment terms, null if x402 is not configured

### `register_agent` (~85 tokens)

Register for an API key

Create an agent identity and receive an API key. Registration is free and includes no free searches.

Input parameters:

- `email` (string, required): Email that will own the account and receive results. Must be the job seeker's own address, and must match cfg_email on every later search
- `name` (string): Display name for the account. Optional; the profile name is used on documents regardless

Output parameters:

- `api_key` (string): Bearer token for every later call. Shown once and never again
- `email` (string): The address the account is registered to
- `error` (string): Present only on failure, e.g. "unauthorized" or "payment_required"
- `message` (string): What to do about the error, when one is present
- `next` (string): Suggested next call
- `note` (string)
- `owner_action_url` (string): Present only on account_owned_by_human. A person already owns this address, so no key can be issued here. Send them to this page to create one and paste it back

### `start_job_search` (~263 tokens)

Start a job search

Spend one credit to run a full search: 7 roles matched to the profile, each with a tailored CV and cover letter returned as markdown by get_search_status and emailed as PDFs. Requires an API key. With no credit left it returns an x402 PaymentRequired; retry the same call with the signed payment in _meta["x402/payment"] to pay in USDC and run immediately.

Input parameters:

- `cv_base64` (string): The job seeker's existing CV as a file, base64 encoded. PDF, DOCX or plain text, up to 10MB. Use cv_json instead if you have the CV as data rather than a file
- `cv_json` (object): The job seeker's existing CV as structured data, in the JSON Resume schema (jsonresume.org): basics, work, education, skills. Prefer this when you hold the CV as data — you do not need to render a fi…
- `cv_type` (string): Format of cv_base64: "pdf", "docx" or "txt". Ignored when cv_json is supplied
- `profile` (object, required): Who the job seeker is and what they want. Every field shapes matching, so guessing is worse than asking

Output parameters:

- `credits_remaining` (number): Credits left for this product after the spend
- `error` (string): Present only on failure, e.g. "unauthorized" or "payment_required"
- `message` (string): What happens next and roughly when, or what to do about the error
- `run_id` (string): Pass this to get_search_status to poll
- `status` (string): Run state at the moment of starting, normally "running"

### `quick_job_search` (~269 tokens)

Quick job match

The single best current role for a profile, with a tailored CV and cover letter, in minutes rather than an hour. $2.50 in USDC. Use this when you want one answer fast; use start_job_search when you want a shortlist of 7 to choose from. With no credit it returns an x402 PaymentRequired; retry the same call with the signed payment in _meta["x402/payment"].

Input parameters:

- `cv_base64` (string): The job seeker's existing CV as a file, base64 encoded. PDF, DOCX or plain text, up to 10MB. Use cv_json instead if you have the CV as data rather than a file
- `cv_json` (object): The job seeker's existing CV as structured data, in the JSON Resume schema (jsonresume.org): basics, work, education, skills. Prefer this when you hold the CV as data — you do not need to render a fi…
- `cv_type` (string): Format of cv_base64: "pdf", "docx" or "txt". Ignored when cv_json is supplied
- `profile` (object, required): Who the job seeker is and what they want. Every field shapes matching, so guessing is worse than asking

Output parameters:

- `credits_remaining` (number): Credits left for this product after the spend
- `error` (string): Present only on failure, e.g. "unauthorized" or "payment_required"
- `message` (string): What happens next and roughly when, or what to do about the error
- `run_id` (string): Pass this to get_search_status to poll
- `status` (string): Run state at the moment of starting, normally "running"

### `get_search_status` (~60 tokens)

Check a search

Progress of a search, and the matched roles with the reason each was picked once it finishes.

Input parameters:

- `run_id` (string): The run_id returned by start_job_search or quick_job_search. Omit to get the most recent run for this account

Output parameters:

- `done` (boolean): True once the run has finished, whether or not it found anything
- `error` (string): Present only on failure, e.g. "unauthorized" or "payment_required"
- `finished_at`
- `matches` (array): The delivered roles, each with its tailored documents. Absent until the run succeeds
- `message` (string): Progress in plain language while running, or what to do about the error
- `plan` (string): Which product this run was: one_off or agent_quick
- `run_id` (string)
- `started_at`
- `status` (string): running, success, no_matches or failed
- `target_jobs` (number): How many roles this run is meant to deliver

## Diagnostics

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

## Score history

- 2026-08-03: 59
- 2026-08-02: 58
- 2026-08-01: 55
- 2026-07-31: 55

## Links

- Remote endpoint: https://jobero.ai/mcp
- Website: https://jobero.ai/agents
- Changelog RSS feed: https://verifymcp.io/servers/ai-jobero-job-search/jobero/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-jobero-job-search/jobero/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-jobero-job-search/jobero