_ registry / mcp streamable-http · checked 1h ago

huntboard

https://huntboard.ai

Registry code: b177485e780684b2

api record

HuntBoard finds real, recent job postings from company career pages and ATS boards (Greenhouse, Lever, Workday, Comeet, Ashby and more), scored against the job seeker's target titles. Call search_jobs with 1-6 target titles and at least one location (or remote_ok: true). Results are already scored 7-10 for fit and deduplicated; show them as a list with the link. get_job returns the full details of one posting from a search_jobs link. list_coverage lists the locations and roles HuntBoard keeps browse pages for. subscribe_daily_hunts emails the person a confirmation link; daily job-match emails…

endpoint
https://huntboard.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is huntboard live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is huntboard free to use?
Yes — the hub reached it with no key and no payment.
What tools does huntboard have?
4 tools: get_job, subscribe_daily_hunts, search_jobs, list_coverage.
Is huntboard safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 99.1%· all time 99.1%

latency
88ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 446 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
used for
  • search recent job postings
  • get job posting details
  • subscribe to daily job alerts
takes → gives
text → data
tools
3 reads1 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
1 open 3 never probed 1 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_coverage reads open 10h ago

    The countries, cities, remote-in-country pages and job roles HuntBoard keeps browse pages for, each with its public page URL. Useful to pick locations and titles before searching.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_job reads unknown 10h ago

    Full details of one posting HuntBoard has indexed: title, company, location, workplace type, employment type, posted date, source, apply link, whether it is still open, and a description excerpt. Pass the link returned by search_jobs.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "maxLength": 1000,
          "minLength": 10,
          "description": "The job link as returned by search_jobs."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • subscribe_daily_hunts changes data unknown never probed

    Ask HuntBoard to email the person new job matches every morning for the given titles and locations. Double opt-in: HuntBoard sends a confirmation link to the email address and nothing starts until the person clicks it. Free, one-click unsubscribe in every email. Only call this when the person explicitly asked for daily emails and gave their own address.

    mcp-tool

    {
      "type": "object",
      "required": [
        "email",
        "titles"
      ],
      "properties": {
        "email": {
          "type": "string",
          "maxLength": 200,
          "minLength": 5,
          "description": "The person's own email address."
        },
        "titles": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80,
            "minLength": 2
          },
          "maxItems": 6,
          "minItems": 1,
          "description": "Target job titles."
        },
        "locations": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80,
            "minLength": 2
          },
          "maxItems": 10,
          "description": "Cities, regions or countries. Optional only when remote_ok is true."
        },
        "remote_ok": {
          "type": "boolean",
          "default": false,
          "description": "Also include remote roles."
        },
        "exclude_titles": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80
          },
          "maxItems": 20
        },
        "exclude_locations": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80
          },
          "maxItems": 20
        }
      },
      "additionalProperties": false
    }
    arguments 58 lines
  • search_jobs reads unknown 10h ago

    Find recent job postings that match target job titles in given locations (or remote). Runs HuntBoard's own hunt: SQL narrowing over its index of company career pages and ATS boards, then an AI fit score. Returns up to max_results jobs scored 7-10 with title, company, location, link, source and a one-line reason.

    mcp-tool

    {
      "type": "object",
      "required": [
        "titles"
      ],
      "properties": {
        "titles": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80,
            "minLength": 2
          },
          "maxItems": 6,
          "minItems": 1,
          "description": "Target job titles, e.g. [\"Backend Engineer\", \"Platform Engineer\"]. Parentheticals are stripped and head phrases matched."
        },
        "locations": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80,
            "minLength": 2
          },
          "maxItems": 10,
          "description": "Cities, regions or countries, e.g. [\"Tel Aviv\", \"Israel\"]. Optional only when remote_ok is true."
        },
        "remote_ok": {
          "type": "boolean",
          "default": false,
          "description": "Also include remote roles open to the given locations (or global remote roles)."
        },
        "max_results": {
          "type": "integer",
          "default": 20,
          "maximum": 50,
          "minimum": 1,
          "description": "How many jobs to return, 1-50."
        },
        "exclude_titles": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80
          },
          "maxItems": 20,
          "description": "Title fragments to drop, e.g. [\"Manager\", \"QA\"]."
        },
        "exclude_locations": {
          "type": "array",
          "items": {
            "type": "string",
            "maxLength": 80
          },
          "maxItems": 20,
          "description": "Location fragments to drop."
        }
      },
      "additionalProperties": false
    }
    arguments 60 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id b177485e780684b2.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/b177485e780684b2/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/b177485e780684b2/badge.svg)](https://brick.blue/agent/b177485e780684b2?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.