_ registry / mcp http-sse · checked 36m ago

browser-forest

https://browserforest.com

Registry code: 2ee4c2c97b834e0c

api record

Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.

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

endpoint
https://browserforest.com/api/mcp
protocol
http-sse ·2025-06-18
authentication
apikey
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 browser-forest live?
Yes — it answered the hub's last check (checked 36m ago). It answered 99% of checks over the last 30 days.
Is browser-forest free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does browser-forest have?
11 tools: mirage_scroll, mirage_extract_text, mirage_wait, mirage_type, mirage_close_session, mirage_navigate, mirage_click, mirage_create_session, ….
Is browser-forest 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
98.8%

90 days 98.8%· all time 98.8%

latency
227ms

last good check

priced tools
0

of 11 tools

_ answered our checks, 90 days 482 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· HTTP 502
  • degraded → live
_ what it is for
topic
search & web browser automation
used for
  • open a cloud browser session
  • navigate and click on pages
  • scrape a url to markdown
  • take a screenshot of a page
takes → gives
text → web pages, text, images
tools
7 reads2 changes data2 effect unclear
_ 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 11 tools
11 never probed 0 of 11 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.

  • mirage_scroll reads unknown never probed

    Scroll the page

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId"
  ],
  "properties": {
    "amount": {
      "type": "number",
      "default": 300,
      "description": "Pixels to scroll"
    },
    "direction": {
      "enum": [
        "up",
        "down",
        "left",
        "right"
      ],
      "type": "string",
      "default": "down"
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 28 lines
  • mirage_extract_text reads unknown never probed

    Extract text content from the current page. For clean main-content text prefer mirage_scrape (markdown/text formats).

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId"
  ],
  "properties": {
    "selector": {
      "type": "string",
      "description": "Optional CSS selector to scope extraction"
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • mirage_wait reads unknown never probed

    Wait for a specified duration

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "milliseconds": {
      "type": "number",
      "default": 1000,
      "description": "Milliseconds to wait"
    }
  },
  "additionalProperties": false
}
    arguments 12 lines
  • mirage_type unknown never probed

    Type text into an input element

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId",
    "selector",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to type"
    },
    "submit": {
      "type": "boolean",
      "description": "Whether to press Enter after typing"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector of the input element"
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • mirage_close_session changes data unknown never probed

    Close a browser session

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId"
  ],
  "properties": {
    "sessionId": {
      "type": "string",
      "description": "The session ID to close"
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • mirage_navigate reads unknown never probed

    Navigate to a URL in the browser session

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId",
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to navigate to"
    },
    "sessionId": {
      "type": "string"
    },
    "waitUntil": {
      "enum": [
        "load",
        "domcontentloaded",
        "networkidle"
      ],
      "type": "string",
      "description": "When to consider navigation complete"
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • mirage_click unknown never probed

    Click an element on the page

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId",
    "selector"
  ],
  "properties": {
    "selector": {
      "type": "string",
      "description": "CSS selector of the element to click"
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • mirage_create_session changes data unknown never probed

    Create a new browser session

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "apiKey"
  ],
  "properties": {
    "apiKey": {
      "type": "string",
      "description": "Your Browser Forest API key (bf_live_...)"
    },
    "timeout": {
      "type": "number",
      "description": "Session timeout in seconds (default 1800)"
    },
    "contextId": {
      "type": "string",
      "description": "Optional context ID to restore browser state"
    },
    "proxyHost": {
      "type": "string"
    },
    "proxyPort": {
      "type": "number"
    },
    "proxyType": {
      "enum": [
        "http",
        "https",
        "socks5"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • mirage_screenshot reads unknown never probed

    Take a screenshot of the current page

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId"
  ],
  "properties": {
    "format": {
      "enum": [
        "png",
        "jpeg"
      ],
      "type": "string",
      "default": "png"
    },
    "fullPage": {
      "type": "boolean",
      "default": false
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • mirage_extract_structured reads unknown never probed

    Extract structured data via in-page JavaScript eval (NOT LLM schema extraction). For field extraction from scraped content, use your own LLM on mirage_scrape output.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "sessionId",
    "script"
  ],
  "properties": {
    "script": {
      "type": "string",
      "description": "JavaScript expression that returns structured data (will be JSON.stringified)"
    },
    "sessionId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • mirage_scrape reads unknown never probed

    Scrape a URL (one-shot, auto-managed session). Prefer format/formats markdown for LLM-ready text. If metadata.mainContentFallback is true or contentProfile is product, do not assume aggressive main-content clipping. Field extraction is BYO-LLM — this tool returns page content/quality metadata, not schema-mapped fields.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to scrape"
    },
    "format": {
      "enum": [
        "html",
        "markdown",
        "text",
        "screenshot"
      ],
      "type": "string",
      "default": "markdown"
    },
    "formats": {
      "type": "array",
      "items": {
        "enum": [
          "markdown",
          "html",
          "rawHtml",
          "text",
          "links",
          "screenshot"
        ],
        "type": "string"
      },
      "minItems": 1,
      "description": "Multi-format output; when set, wins over format"
    },
    "waitFor": {
      "enum": [
        "load",
        "domcontentloaded",
        "networkidle"
      ],
      "type": "string"
    },
    "selector": {
      "type": "string",
      "description": "CSS selector to extract; ignores onlyMainContent"
    },
    "onlyMainContent": {
      "type": "boolean",
      "description": "Prefer main-content clipping; ignored when selector is set"
    }
  },
  "additionalProperties": false
}
    arguments 56 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 2ee4c2c97b834e0c.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/2ee4c2c97b834e0c/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/2ee4c2c97b834e0c/badge.svg)](https://brick.blue/agent/2ee4c2c97b834e0c?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.