Skip to content
BlockReq logo

BlockReq MCP server

Which MCP servers are BlockReq'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 2026-10-20

← Back to BlockReq

Whose server it is
  • Registry namecom.blockreq/rpcverified in the MCP registry

The registry name sits under blockreq.com. 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
  • Tools6
  • Server calls itselfblockreq
  • 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 250 ms.

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

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: 8, the first on 2026-10-20
  • INITE MCP score99 of 100answers 100 · definitions 97 · context 100 · connects 100
  • Answered100% of days8 of 8 daily checks
  • Median first answer256 ms
  • Space in an agent's context≈ 886 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 97 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 6

What an agent can do with it

  • not sure · read historical contract state at past blocks
  • not sure · trace transactions and blocks for debugging
  • not sure · connect viem, ethers, or Foundry to a hosted endpoint

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 offers6 tools · read 2026-10-20
  • list_chains

    List every published BlockReq network with its host, public trial URL, private URL pattern ({API_KEY} placeholder), WSS support, and archive and proof/debug/trace flags.

  • get_chain

    Get one network's URLs and capability flags, its API reference page, and (for EVM networks) the JSON-RPC methods documented for it.

  • search_docs

    Search the BlockReq docs (setup, API keys, endpoints, Request Counting, plans, networks, support). Returns page titles, URLs, Markdown URLs for get_doc_page, and snippets. Chinese queries search the Chinese pages.

  • get_doc_page

    Read one BlockReq docs page as Markdown. Accepts a https://blockreq.com/docs/... URL (HTML or index.md) or a path such as /docs/getting-started/.

  • get_method_reference

    Get the documented parameters, result, example, and endpoints of one JSON-RPC method on one EVM network, from BlockReq's OpenRPC document.

  • call_rpc

    Call one read-only JSON-RPC method on an EVM network. Without credentials it uses the public trial endpoint (rate-limited, recent state only); when this MCP connection sends a BlockReq API key or is signed in to a BlockReq account, it…

How to connect

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

{
  "mcpServers": {
    "rpc": {
      "type": "http",
      "url": "https://mcp.blockreq.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http blockreq https://mcp.blockreq.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.blockreq.com/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.