_ registry / mcp http-sse · checked 5h ago

AutoApply

https://autoapply-mcp.onrender.com

Registry code: 6031032a816e3682

api record

Automates job applications using a real browser to fill forms on Greenhouse, Lever, Workday, and LinkedIn.

from a public catalogue that lists it, not from the operator

endpoint
https://autoapply-mcp.onrender.com/mcp
protocol
http-sse ·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 AutoApply live?
Yes — it answered the hub's last check (checked 5h ago). It answered 84% of checks over the last 30 days.
Is AutoApply free to use?
Yes — the hub reached it with no key and no payment.
What tools does AutoApply have?
10 tools: save_profile, scroll_page, fill_known_fields, register, take_screenshot, save_field_mapping, open_job_application, fill_answer, ….
Is AutoApply 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
83.6%

90 days 86.6%· all time 86.6%

latency
605ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 284 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • degraded → down· timeout after 20000ms
  • live → degraded· timeout after 20000ms
_ what it is for
topic
productivity & business hr & recruiting
used for
  • open a job application form
  • auto-fill a job application
  • save an applicant profile
  • take a screenshot of the form
takes → gives
web pages, data → images, data
tools
2 reads8 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 10 tools
10 never probed 0 of 10 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.

  • save_profile changes data unknown never probed

    Save your job application profile (name, email, phone, address, work auth, etc.). Stored server-side keyed to your session_id.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id",
    "profile"
  ],
  "properties": {
    "profile": {
      "type": "object",
      "properties": {
        "salary": {
          "type": "object",
          "properties": {
            "desiredMin": {
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "personal": {
          "type": "object",
          "properties": {
            "email": {
              "type": "string",
              "format": "email"
            },
            "phone": {
              "type": "string"
            },
            "github": {
              "type": "string",
              "format": "uri"
            },
            "address": {
              "type": "object",
              "properties": {
                "zip": {
                  "type": "string"
                },
                "city": {
                  "type": "string"
                },
                "state": {
                  "type": "string"
                },
                "street": {
                  "type": "string"
                },
                "country": {
                  "type": "string",
                  "default": "United States"
                }
              },
              "additionalProperties": false
            },
            "lastName": {
              "type": "string"
            },
            "linkedIn": {
              "type": "string",
              "format": "uri"
            },
            "firstName": {
              "type": "string"
            },
            "hearAbout": {
              "type": "string",
              "default": "LinkedIn"
            },
            "portfolio": {
              "type": "string",
              "format": "uri"
            },
            "willingToRelocate": {
              "type": "boolean",
              "default": true
            }
          },
          "additionalProperties": false
        },
        "education": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "degree": {
                "type": "string"
              },
              "institution": {
                "type": "string"
              }
            },
            "additionalProperties": false
          }
        },
        "demographics": {
          "type": "object",
          "properties": {
            "gender": {
              "type": "string"
            },
            "ethnicity": {
              "type": "string"
            },
            "veteranStatus": {
              "type": "string"
            },
            "authorizedToWork": {
              "type": "boolean",
              "default": true
            },
            "disabilityStatus": {
              "type": "string"
            },
            "requiresSponsorship": {
              "type": "boolean",
              "default": false
            }
          },
          "additionalProperties": false
        }
      },
      "description": "Your job application profile",
      "additionalProperties": false
    },
    "session_id": {
      "type": "string",
      "description": "Your API key from register"
    }
  },
  "additionalProperties": false
}
    arguments 133 lines
  • scroll_page changes data unknown never probed

    Scroll the job application page up or down to reveal more fields.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id"
  ],
  "properties": {
    "amount": {
      "type": "integer",
      "default": 800,
      "maximum": 5000,
      "minimum": 100,
      "description": "Pixels to scroll"
    },
    "direction": {
      "enum": [
        "down",
        "up"
      ],
      "type": "string",
      "default": "down"
    },
    "session_id": {
      "type": "string",
      "description": "Your session ID"
    }
  },
  "additionalProperties": false
}
    arguments 29 lines
  • fill_known_fields changes data unknown never probed

    Auto-fill all mapped fields (name, email, phone, dropdowns, etc.) from your saved profile. Returns a screenshot and a list of unique questions that need AI answers.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id",
    "profile"
  ],
  "properties": {
    "profile": {
      "type": "object",
      "description": "User profile JSON (from get_profile or save_profile)",
      "additionalProperties": {}
    },
    "session_id": {
      "type": "string",
      "description": "Your session ID"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • register changes data unknown never probed

    Get a new API key / session ID. Call this once before using any other tools.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
    arguments 5 lines
  • take_screenshot reads unknown never probed

    Take a screenshot of the current state of the job application page.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "Your session ID"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • save_field_mapping changes data unknown never probed

    Teach AutoApply how to answer a recurring question. Provide the label pattern (partial match is fine) and the answer to always use. Example: pattern='located in san francisco', value='Yes'. Next time fill_known_fields sees that label, it fills it automatically.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id",
    "pattern",
    "value"
  ],
  "properties": {
    "value": {
      "type": "string",
      "description": "Answer to always fill for this field (e.g. 'Yes', 'No', 'San Francisco')"
    },
    "pattern": {
      "type": "string",
      "description": "Label text to match (e.g. 'us citizen', 'located in san francisco bay area')"
    },
    "session_id": {
      "type": "string",
      "description": "Your API key"
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • open_job_application changes data unknown never probed

    Open a job application URL in a browser and return a screenshot. Always call this before fill_known_fields.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url",
    "session_id"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Full URL of the job application page"
    },
    "session_id": {
      "type": "string",
      "description": "Your session ID (same as API key)"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • fill_answer changes data unknown never probed

    Fill a specific answer into one field. Use the selector from unique_questions returned by fill_known_fields. Call this once per unique question after generating each answer.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id",
    "selector",
    "answer"
  ],
  "properties": {
    "answer": {
      "type": "string",
      "description": "The answer text to fill in"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector for the field (from unique_questions)"
    },
    "session_id": {
      "type": "string",
      "description": "Your session ID"
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • close_session changes data unknown never probed

    Close the browser session when done. Always call this after submitting or abandoning.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "Your session ID"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • get_profile reads unknown 14h ago

    Retrieve your saved profile to review or update it.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "Your API key"
    }
  },
  "additionalProperties": false
}
    arguments 14 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 6031032a816e3682.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/6031032a816e3682/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/6031032a816e3682/badge.svg)](https://brick.blue/agent/6031032a816e3682?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
100%

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.