Skip to content
BidSurvivor logo

BidSurvivor MCP server

Which MCP servers are BidSurvivor's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-21

← Back to BidSurvivor

Whose server it is
  • Registry namespace.bidsurvivor/boardverified in the MCP registry

The registry name sits under bidsurvivor.space. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools7
  • Server calls itselfbidsurvivor
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 160 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "Track which brands lead the ranked hall of bids", the likely first call is list_winners.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 15, the first on 2026-10-21
  • INITE MCP score99 of 100answers 100 · definitions 98 · context 100 · connects 100
  • Answered100% of days15 of 15 daily checks
  • Median first answer473 ms
  • Space in an agent's context≈ 1,057 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsA · 98 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 7

What an agent can do with it

  • not sure · Bid on a twelve-hour logo ad slot
  • not sure · List a website for daily ad-slot auctions
  • can do · Track which brands lead the ranked hall of bids

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers7 tools · read 2026-10-21
  • get_board

    The live advertising board: 2 slots a day of 12 hours each, showing which are held, by whom, for how much, and which are free. A slot with isFree true can be claimed for nothing with claim_free_slot.

  • get_slot_price

    What it costs to take a specific slot right now: zero if nobody holds it, otherwise the amount a bid has to beat.

  • claim_free_slot

    Put a product on the board in a slot nobody holds. Costs nothing: an empty slot has no standing bid to beat, so any amount takes it, zero included. No account and no card. The name, logo and description are read from the site…

  • list_brands

    Every brand that has held or contested a twelve-hour advertising slot, newest attention first, optionally filtered to one category. Each row carries what the placement delivered — card opens and click-throughs — and whether the brand bid…

  • get_brand_stats

    The published numbers for one brand: slots held, card opens, and click-throughs to its own site. These are the same figures anyone can read on the site.

  • list_winners

    Brands that held a slot when it closed — plus whoever is leading the live slot right now — ranked by what they paid, over the last 7 days, 30 days or a year. Optionally filtered to one category.

  • get_stats

    How much attention the board actually sends: visitors, page views, and click-throughs to brands. Published rather than claimed — this is a small board and the numbers say so.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "board": {
      "type": "http",
      "url": "https://bidsurvivor.space/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http bidsurvivor https://bidsurvivor.space/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://bidsurvivor.space/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.