_ registry / mcp http-sse · checked 57m ago

obelisk

https://api.obeliskapp.io

Registry code: 493b44e393906f24

api record

Call get_account first to confirm tenant, subscription, credits, and scopes. Always set external_id on create_generation_job and create_post so retries are idempotent. After create_generation_job, poll get_job until the job is terminal. Publishing via create_post creates TikTok drafts the user finishes in the TikTok app; it does not go live. Use identifiers returned by prior calls; do not invent ids.

endpoint
https://api.obeliskapp.io/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
10 · newcomer
_ is it live, free and safe measured by this hub
Is obelisk live?
Yes — it answered the hub's last check (checked 57m ago). It answered 100% of checks over the last 30 days.
Is obelisk free to use?
Yes — the hub reached it with no key and no payment.
What tools does obelisk have?
9 tools: get_ad, get_facebook_company_ads, search_facebook_ads, search_facebook_companies, get_google_ads, search_brands, search_ads, get_brand, ….
Is obelisk 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
99.6%

90 days 99.2%· all time 99.3%

latency
148ms

last good check

priced tools
0

of 9 tools

_ answered our checks, 90 days 775 checks · signed record
  • degraded → live
  • live → degraded· fetch failed
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
productivity & business marketing & seo
used for
  • search competitor ads
  • look up live facebook and google ads
  • find advertiser brands
  • generate ad creatives
takes → gives
text → data
tools
9 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
9

distinct

settlements
12

last 2026-11-09

received on chain
0.12 USDC

no flags

_ what it can do 9 tools
1 open 8 never probed 1 of 9 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_models reads open 7h ago

    Use this when you need generation model ids and their default credit costs before creating a job. Required scope: generation. Free.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "description": "Filter: image, video, or audio"
    }
  },
  "additionalProperties": false
}
    arguments 10 lines
  • get_ad reads unknown 57m ago

    Use this when you already have a spy ad id and need that one record. Do not use to search; call search_ads first. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Spy ad id"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_facebook_company_ads reads unknown never probed

    Use this when you already have a Facebook page id and need its live ads. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "required": [
    "page_id"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "offset": {
      "type": "integer"
    },
    "country": {
      "type": "string"
    },
    "page_id": {
      "type": "string",
      "description": "Facebook page id"
    },
    "media_type": {
      "type": "string"
    },
    "ad_active_status": {
      "type": "string"
    },
    "publisher_platform": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      }
    }
  },
  "additionalProperties": false
}
    arguments 37 lines
  • search_facebook_ads reads unknown never probed

    Use this when you need live Facebook ads. Do not use for the indexed spy catalog; call search_ads for that. Required scope: discovery. Costs 1 credit per request. Typical flow: search_facebook_ads → create_generation_job → get_job → create_post.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "query": {
      "type": "string",
      "description": "Search query"
    },
    "offset": {
      "type": "integer"
    },
    "country": {
      "type": "string"
    },
    "end_date": {
      "type": "string"
    },
    "media_type": {
      "type": "string"
    },
    "start_date": {
      "type": "string"
    },
    "ad_active_status": {
      "type": "string"
    },
    "publisher_platform": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      }
    }
  },
  "additionalProperties": false
}
    arguments 43 lines
  • search_facebook_companies reads unknown never probed

    Use this when you need live Facebook advertiser pages. Do not use for indexed spy brands; call search_brands for that. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer"
    },
    "query": {
      "type": "string",
      "description": "Company search query"
    },
    "offset": {
      "type": "integer"
    },
    "country": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • get_google_ads reads unknown 7h ago

    Use this when you need live Google ads by company domain or advertiser id. Do not use for Facebook ads. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer"
    },
    "topic": {
      "type": "string"
    },
    "domain": {
      "type": "string",
      "description": "Company domain. Provide exactly one of domain or advertiser_id."
    },
    "offset": {
      "type": "integer"
    },
    "region": {
      "type": "string"
    },
    "end_date": {
      "type": "string"
    },
    "start_date": {
      "type": "string"
    },
    "advertiser_id": {
      "type": "string",
      "description": "Google advertiser id. Provide exactly one of domain or advertiser_id."
    },
    "get_ad_details": {
      "type": [
        "null",
        "boolean"
      ]
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • search_brands reads unknown 57m ago

    Use this when you need spy brands by name or domain from the indexed catalog. Do not use for live Facebook pages; call search_facebook_companies for that. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer"
    },
    "order": {
      "type": "string"
    },
    "query": {
      "type": "string",
      "description": "Brand name search. Provide exactly one of query or domain."
    },
    "domain": {
      "type": "string",
      "description": "Domain search. Provide exactly one of query or domain."
    },
    "offset": {
      "type": "integer"
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • search_ads reads unknown 7h ago

    Use this when you need ads from Obelisk's indexed spy catalog. Do not use for live Facebook ad-library results; call search_facebook_ads for that. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "live": {
      "type": [
        "null",
        "boolean"
      ]
    },
    "limit": {
      "type": "integer"
    },
    "niche": {
      "type": "string"
    },
    "offset": {
      "type": "integer"
    },
    "brand_id": {
      "type": "string"
    },
    "language": {
      "type": "string"
    },
    "platform": {
      "type": "string"
    },
    "market_target": {
      "type": "string"
    },
    "display_format": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • get_brand reads unknown 57m ago

    Use this when you already have a spy brand id. Do not use to search; call search_brands first. Required scope: discovery. Costs 1 credit per request.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Spy brand id"
    },
    "include_ads": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "Include ads on the brand. Defaults to true."
    }
  },
  "additionalProperties": false
}
    arguments 20 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 493b44e393906f24.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/493b44e393906f24/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/493b44e393906f24/badge.svg)](https://brick.blue/agent/493b44e393906f24?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.