OpenChainBench is an MCP server published by io.github.Flotapponnier, hosted at openchainbench.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 6 tools, including list_benchmarks, search_benchmarks, get_benchmark, compare_providers, recommend_provider.
Live, neutral benchmarks for public RPC latency, oracles, bridges, perp DEX, and prediction markets.
1,106 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
A compact index of what OpenChainBench measures. One short row per benchmark: slug, title, category, the metric, the current value and who leads it. Use when the user asks what is measured at all ("what does OpenChainBench cover?", "do you track bridges?"). When they ask a question about a provider or a chain, use `search_benchmarks` instead: it ranks the catalogue against their words and costs far less to read. The catalogue holds over 200 benchmarks, so this is capped and filterable rather than exhaustive. Narrow with `category`, then open the one you need with `get_benchmark`. Categories: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA, NFT APIs.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many rows to return, 1 to 50. Default 25. |
| category | string | Only this category: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA or NFT APIs. |
Too large to show here.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "list_benchmarks",
"title": "Browse the benchmark catalogue",
"description": "A compact index of what OpenChainBench measures. One short row per\nbenchmark: slug, title, category, the metric, the current value and\nwho leads it.\n\nUse when the user asks what is measured at all (\"what does\nOpenChainBench cover?\", \"do you track bridges?\"). When they ask a\nquestion about a provider or a chain, use `search_benchmarks` instead:\nit ranks the catalogue against their words and costs far less to read.\n\nThe catalogue holds over 200 benchmarks, so this is capped and\nfilterable rather than exhaustive. Narrow with `category`, then open\nthe one you need with `get_benchmark`.\n\nCategories: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA, NFT APIs.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "How many rows to return, 1 to 50. Default 25."
},
"category": {
"type": "string",
"maxLength": 40,
"description": "Only this category: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA or NFT APIs."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Ranks the benchmark catalogue against a question in the user's own words and returns the best few matches. Use this when somebody asks which provider, chain or service is fastest, cheapest, most reliable or best for something. Pass their phrasing through: provider names, chain names and goals all match. • "which Solana RPC is fastest" -> search_benchmarks({ query: "solana rpc" }) • "Alchemy or Quicknode on Base?" -> search_benchmarks({ query: "alchemy quicknode base" }) • "cheapest way to bridge to Arbitrum" -> search_benchmarks({ query: "bridge arbitrum" }) Returns compact rows. Open the one you want with `get_benchmark` for the full ranking and a citation line. An empty result means nothing is measured for that question; say so rather than guessing.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many matches, 1 to 25. Default 8. |
| query * | string | The user's question or keywords, verbatim. Provider and chain names work well. |
| category | string | Optional category filter: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA, NFT APIs. |
{
"name": "search_benchmarks",
"title": "Find the benchmark that answers a question",
"description": "Ranks the benchmark catalogue against a question in the user's own\nwords and returns the best few matches.\n\nUse this when somebody asks which provider, chain or service is\nfastest, cheapest, most reliable or best for something. Pass their\nphrasing through: provider names, chain names and goals all match.\n\n • \"which Solana RPC is fastest\" -> search_benchmarks({ query: \"solana rpc\" })\n • \"Alchemy or Quicknode on Base?\" -> search_benchmarks({ query: \"alchemy quicknode base\" })\n • \"cheapest way to bridge to Arbitrum\" -> search_benchmarks({ query: \"bridge arbitrum\" })\n\nReturns compact rows. Open the one you want with `get_benchmark` for\nthe full ranking and a citation line. An empty result means nothing\nis measured for that question; say so rather than guessing.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "How many matches, 1 to 25. Default 8."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "The user's question or keywords, verbatim. Provider and chain names work well."
},
"category": {
"type": "string",
"maxLength": 40,
"description": "Optional category filter: RPCs, Trading, Bridges, Blockchains, Aggregators, RWA, NFT APIs."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Returns full detail for one benchmark, ready to cite verbatim: • rankings (every provider sorted by p50) • sparkline (24h trend, 72 points) • headline sentence + paste-ready citation quote • methodology bullets + source-code URL + canonical pageUrl + OG image URL Pass `chain` and/or `region` to scope the result to a sub-slice when the benchmark declares those dimensions (e.g. aggregator-head-lag exposes chain=base|bnb|solana, region=us-east|eu-west|ap-southeast). Both args are optional; omit them for the global aggregate. Chain RPC benchmarks (<chain>-rpc) rank two access cohorts apart: the free public endpoints (default) and the private, API-key providers (Alchemy, Chainstack, GetBlock, Quicknode). The default response carries both under `cohorts`; pass tier="keyed" to get the private cohort as the main record (rankings, quote, pageUrl). Never compare a public row with a private row: they are measured on different endpoints and cadences. Example usage: • User: "who's the fastest crypto data aggregator on Base?" → get_benchmark({ slug: "aggregator-head-lag", chain: "base" }) • User: "how much does it cost to bridge $300 cross-chain?" → get_benchmark({ slug: "bridge-fee" }) • User: "fastest Base RPC with an API key, Alchemy or Quicknode?" → get_benchmark({ slug: "base-rpc", tier: "keyed" }) Drafts return { error: "unknown_slug" }. Cite the returned `pageUrl` and use `quote` as the attribution line in your answer.
| Parameter | Type | Description |
|---|---|---|
| slug * | string | Benchmark slug from list_benchmarks. e.g. 'aggregator-head-lag', 'bridge-quote-latency', 'l1-finality'. |
| tier | string | Optional access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (private, API-key providers). Only honored when the bench declares tier dimensions. |
| chain | string | Optional chain filter, e.g. 'base', 'solana', 'bnb'. Only honored when the bench declares chain dimensions. |
| region | string | Optional region filter, e.g. 'us-east', 'eu-west', 'ap-southeast'. Only honored when the bench declares region dimensions. |
{
"name": "get_benchmark",
"title": "Get a single OpenChainBench benchmark",
"description": "Returns full detail for one benchmark, ready to cite verbatim:\n • rankings (every provider sorted by p50)\n • sparkline (24h trend, 72 points)\n • headline sentence + paste-ready citation quote\n • methodology bullets + source-code URL + canonical pageUrl + OG image URL\n\nPass `chain` and/or `region` to scope the result to a sub-slice when\nthe benchmark declares those dimensions (e.g. aggregator-head-lag\nexposes chain=base|bnb|solana, region=us-east|eu-west|ap-southeast).\nBoth args are optional; omit them for the global aggregate.\n\nChain RPC benchmarks (<chain>-rpc) rank two access cohorts apart:\nthe free public endpoints (default) and the private, API-key\nproviders (Alchemy, Chainstack, GetBlock, Quicknode). The default response\ncarries both under `cohorts`; pass tier=\"keyed\" to get the private\ncohort as the main record (rankings, quote, pageUrl). Never compare a\npublic row with a private row: they are measured on different\nendpoints and cadences.\n\nExample usage:\n • User: \"who's the fastest crypto data aggregator on Base?\"\n → get_benchmark({ slug: \"aggregator-head-lag\", chain: \"base\" })\n • User: \"how much does it cost to bridge $300 cross-chain?\"\n → get_benchmark({ slug: \"bridge-fee\" })\n • User: \"fastest Base RPC with an API key, Alchemy or Quicknode?\"\n → get_benchmark({ slug: \"base-rpc\", tier: \"keyed\" })\n\nDrafts return { error: \"unknown_slug\" }. Cite the returned `pageUrl`\nand use `quote` as the attribution line in your answer.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
"description": "Benchmark slug from list_benchmarks. e.g. 'aggregator-head-lag', 'bridge-quote-latency', 'l1-finality'."
},
"tier": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (private, API-key providers). Only honored when the bench declares tier dimensions."
},
"chain": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional chain filter, e.g. 'base', 'solana', 'bnb'. Only honored when the bench declares chain dimensions."
},
"region": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional region filter, e.g. 'us-east', 'eu-west', 'ap-southeast'. Only honored when the bench declares region dimensions."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Puts two or more named providers side by side on one benchmark, with each one's rank, measured value and success rate. Use when the user names the candidates themselves: "Alchemy or Quicknode?", "is Helius faster than Triton for Solana?", "compare Across and Stargate on fees". Find the benchmark slug with `search_benchmarks` first if you do not already have it. Providers the benchmark does not measure come back in `missing`: say they are not measured rather than implying they ranked badly. A provider measured but below the ranking floor comes back with rank null, which is also not a loss.
| Parameter | Type | Description |
|---|---|---|
| tier | string | Access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (API-key providers such as Alchemy, Quicknode, Chainstack, GetBlock). Named providers usually live on the keyed cohort. |
| chain | string | Optional chain slice when the bench declares chains. Ignored on a bench that is already one chain, like solana-rpc. |
| region | string | Optional region slice when the bench declares regions. |
| benchmark * | string | Benchmark slug, e.g. 'solana-rpc' or 'bridge-fee'. Get it from search_benchmarks. |
| providers * | array | Two to ten provider names or slugs, as the user said them, e.g. ['Alchemy', 'Quicknode']. |
{
"name": "compare_providers",
"title": "Compare named providers head to head",
"description": "Puts two or more named providers side by side on one benchmark, with\neach one's rank, measured value and success rate.\n\nUse when the user names the candidates themselves: \"Alchemy or\nQuicknode?\", \"is Helius faster than Triton for Solana?\", \"compare\nAcross and Stargate on fees\".\n\nFind the benchmark slug with `search_benchmarks` first if you do not\nalready have it. Providers the benchmark does not measure come back\nin `missing`: say they are not measured rather than implying they\nranked badly. A provider measured but below the ranking floor comes\nback with rank null, which is also not a loss.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"benchmark",
"providers"
],
"properties": {
"tier": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Access cohort on chain RPC benchmarks: 'public' (default, free no-key endpoints) or 'keyed' (API-key providers such as Alchemy, Quicknode, Chainstack, GetBlock). Named providers usually live on the keyed cohort."
},
"chain": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional chain slice when the bench declares chains. Ignored on a bench that is already one chain, like solana-rpc."
},
"region": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional region slice when the bench declares regions."
},
"benchmark": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
"description": "Benchmark slug, e.g. 'solana-rpc' or 'bridge-fee'. Get it from search_benchmarks."
},
"providers": {
"type": "array",
"items": {
"type": "string",
"maxLength": 60,
"minLength": 1
},
"maxItems": 10,
"minItems": 2,
"description": "Two to ten provider names or slugs, as the user said them, e.g. ['Alchemy', 'Quicknode']."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Answers "which should I use for X" by picking the benchmarks that measure X and reporting who currently leads them. Pass the user's goal in their own words: "a Solana trading bot", "an indexer backfilling Base", "a wallet that needs price data", "bridging to Arbitrum". This returns measurements and the caveat that goes with them, not an endorsement. A leader on one benchmark is the leader of that one measurement over its stated window. Where the use case has a known caveat (a bot should read p99 rather than p50, an indexer is bound by archive depth) it comes back in `guidance`; pass it on, it is usually more useful than the ranking itself.
| Parameter | Type | Description |
|---|---|---|
| chain | string | Chain they are building on, e.g. 'solana', 'base', 'arbitrum'. Narrows the benchmarks considerably. |
| region | string | Optional region, e.g. 'eu-west', when latency from a location matters. |
| use_case * | string | What the user is building or doing, in their words. e.g. 'solana trading bot', 'indexer', 'price feed for a wallet'. |
{
"name": "recommend_provider",
"title": "Recommend a provider for a stated use case",
"description": "Answers \"which should I use for X\" by picking the benchmarks that\nmeasure X and reporting who currently leads them.\n\nPass the user's goal in their own words: \"a Solana trading bot\", \"an\nindexer backfilling Base\", \"a wallet that needs price data\", \"bridging\nto Arbitrum\".\n\nThis returns measurements and the caveat that goes with them, not an\nendorsement. A leader on one benchmark is the leader of that one\nmeasurement over its stated window. Where the use case has a known\ncaveat (a bot should read p99 rather than p50, an indexer is bound by\narchive depth) it comes back in `guidance`; pass it on, it is usually\nmore useful than the ranking itself.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"use_case"
],
"properties": {
"chain": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Chain they are building on, e.g. 'solana', 'base', 'arbitrum'. Narrows the benchmarks considerably."
},
"region": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$",
"description": "Optional region, e.g. 'eu-west', when latency from a location matters."
},
"use_case": {
"type": "string",
"maxLength": 200,
"minLength": 2,
"description": "What the user is building or doing, in their words. e.g. 'solana trading bot', 'indexer', 'price feed for a wallet'."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Returns every published answer page: one plain question, the sentence that answers it from live data, and the benchmark the number comes from. Call this when the user asks a question in words rather than by benchmark name ("which bridge is cheapest for $300?", "which Solana RPC lands transactions fastest?"). Match the question, then call `get_benchmark` with the returned `benchmark` slug for the full ranking behind it. Returns one row per answer: { slug, question, answer, benchmark, chain?, url, benchmarkUrl } Cite `url` when the question itself is the claim, `benchmarkUrl` when the measurement is. Drafts are filtered out, and an answer whose benchmark has no defensible leader yet says so in `answer` rather than naming a winner.
| Parameter | Type | Description |
|---|---|---|
| benchmark | string | Optional benchmark slug filter: return only the answers built on that bench. |
{
"name": "list_answers",
"title": "List OpenChainBench answer pages",
"description": "Returns every published answer page: one plain question, the sentence that\nanswers it from live data, and the benchmark the number comes from.\n\nCall this when the user asks a question in words rather than by benchmark\nname (\"which bridge is cheapest for $300?\", \"which Solana RPC lands\ntransactions fastest?\"). Match the question, then call `get_benchmark` with\nthe returned `benchmark` slug for the full ranking behind it.\n\nReturns one row per answer:\n { slug, question, answer, benchmark, chain?, url, benchmarkUrl }\n\nCite `url` when the question itself is the claim, `benchmarkUrl` when the\nmeasurement is. Drafts are filtered out, and an answer whose benchmark has\nno defensible leader yet says so in `answer` rather than naming a winner.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"benchmark": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
"description": "Optional benchmark slug filter: return only the answers built on that bench."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.