Skip to content
Bidit logo

Bidit MCP server

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

read 2026-10-20

← Back to Bidit

Whose server it is
  • Registry nameau.com.bidit/registryverified in the MCP registry

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

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools4
  • Server calls itselfbidit-registry
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 172 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-10-20
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer133 ms
  • Space in an agent's context≈ 638 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Every tool passes all six checks.

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 offers4 tools · read 2026-10-20
  • will_price_match

    Returns whether a retailer publishes a policy of matching a competitor's lower price, with the verified terms, exclusions, how to claim, a sentence quoted from the policy and the policy page. answer is yes (a person has verified the…

  • price_policy

    Returns everything the Registry has verified about how a retailer handles price: whether it takes offers through Bidit, whether it price matches and on what terms, how it runs promotions, and its clearance page. Fields are null where…

  • retailers_that_price_match

    Returns the retailers whose price-match policy a person has verified, optionally filtered by category and country, each with its terms and policy page. A retailer absent from the list is unverified, not a no.

  • can_make_offer

    Returns whether a shopper can make this retailer an offer instead of paying the listed price. answer is yes (the retailer accepts offers through Bidit now; offers_url is where) or not_yet (the retailer does not; register_interest_url and…

How to connect

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

{
  "mcpServers": {
    "registry": {
      "type": "http",
      "url": "https://registry.bidit.com.au/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http bidit https://registry.bidit.com.au/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://registry.bidit.com.au/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.