ChainChoice MCP server

• Registry nameio.chainchoice/rankingsverified in the MCP registry

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

• Stateanswerschecked 2026-11-04
• Tools7
• Server calls itselfio.chainchoice/rankings
• Server version1.3.0
• Protocol version2025-06-18

On 2026-11-04 the server answered initialize and tools/list without a sign-in. First answer in 249 ms.

• 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.

• 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 answer247 ms
• Space in an agent's context≈ 1,406 tokensthe definitions of all its tools (7), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

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 →

• list_categories

  Every category ChainChoice ranks, with how many products it ranks, how many it assessed and left out with a reason, its leader, and its page.

• get_ranking

  The published order of one category: rank, product id, name and ChainChoice Score, with the methodology version, the dimension weights and what was assessed. The same order the category page and rankings.json publish.

• get_ranking_for_country

  The category's products as a reader in one country sees them: those available there, in order, with each one's published score and rank beside it. When nothing passes the country's availability filter, resultMode is "fallback" and the…

• get_evidence

  For one category (and optionally one product id): each criterion, its weight, and per product the score with the quoted passage, its source URL and the day it was read.

• verify_receipt

  Checks a signed receipt (as ChainChoice serves it, or an issuer envelope) against the keys ChainChoice publishes: whether its content hash matches and its signature is valid. The same verifier as POST /api/v1/verify.

• search

  Reads a query exactly as ChainChoice's search bars do (the same resolver as the homepage, the navigation field and the command palette) and returns that reading: the page it opens (a category's ranked list with the country, monthly…

• hand_off

  Once the reader has agreed to go to a provider (consent: true), returns what to hand over: the provider's own address as ChainChoice's catalog records it (never a referral or affiliate link; ChainChoice earns nothing from it), the…