About Bitview
Bitview is a read-only MCP server for Bitcoin blockchain, mempool, mining, market and on-chain analytics, requiring no API key. It is a stateless adapter that forwards tool calls as GET requests to the Bitview REST API.
Key features
- 01Read-only blockchain and mempool data
- 02Mining and market data queries
- 03On-chain analytics metrics
- 04No authentication required
- 05Tool catalog generated from OpenAPI
Use cases
- 01Looking up Bitcoin block and transaction information
- 02Monitoring mempool and mining status
- 03Analyzing on-chain data and market indicators
MCP support
The server exposes the Bitview REST API operations as generated MCP tools over a Streamable HTTP endpoint and forwards each call to the upstream REST API.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.bitview.space/claude mcp add --transport http bitcoinresearchkit-bitview https://mcp.bitview.space/{"mcpServers":{"bitcoinresearchkit-bitview":{"type":"http","url":"https://mcp.bitview.space/"}}}Open in Cursor{"servers":{"bitcoinresearchkit-bitview":{"type":"http","url":"https://mcp.bitview.space/"}}}Open in VS Code{"mcpServers":{"bitcoinresearchkit-bitview":{"type":"http","url":"https://mcp.bitview.space/"}}}{"mcpServers":{"bitcoinresearchkit-bitview":{"serverUrl":"https://mcp.bitview.space/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEbitview_mcp
bitview_mcp is a thin, stateless, read-only MCP adapter for the Bitview REST API. It
exposes the MCP-visible OpenAPI operations as generated tools and forwards
every tool call to the configured public REST origin as a GET request.
The official public endpoint is mcp.bitview.space. It is stateless, read-only, and requires no authentication.
A server built from the current source also serves an instance landing page,
/privacy, /terms, /support, and /logo.png. The icon is embedded in the
binary and advertised in MCP discovery metadata. These instance-local routes
are separate from the MCP protocol and may not be available on older deployed
versions.
Caching model
bitview_mcp does not cache API responses or retain MCP sessions. Point it at the
public Cloudflare-fronted REST origin so its upstream GET requests use the
existing Cloudflare cache:
MCP client -> bitview_mcp -> Cloudflare-cached REST API -> Bitview server
Cloudflare does not need to cache the MCP endpoint. The MCP catalog TTL is only a standard client-side cache hint for the static discovery and tool-list metadata.
Run
From the workspace:
cargo run -p bitview_mcp -- \
--api https://bitview.space \
--url https://mcp.bitview.space/ \
--name Bitview
Or run an installed binary:
bitview_mcp \
--api https://api.example.com \
--url https://mcp.example.com/ \
--name "Example Node"
All three options are required:
--apiis the upstream Bitview REST origin. A bare host tries HTTPS first and retries over HTTP only if HTTPS fails at the transport layer.--urlis this server's public MCP URL. It must be an absolute HTTP(S) origin.--nameis the human-readable instance name shown on the landing page and in MCP discovery metadata.
For local development:
bitview_mcp \
--api http://127.0.0.1:3110 \
--url http://127.0.0.1:3111/ \
--name "Local Bitview"
The Streamable HTTP endpoint is http://127.0.0.1:3111/ by default. If that
port is unavailable, the server tries each port through 3211. The server
supports MCP protocol version 2026-07-28.
Both URLs must be origins without a path, query, or credentials. The public URL is normalized with a trailing slash.
Generated catalog
The tool catalog is generated from the canonical OpenAPI document by
bitview_bindgen and embedded in the binary at compile time from
generated/manifest.json. Do not edit the generated manifest by hand; after
changing the API, run:
cargo run -p bitviewd --example bindgen --features bindgen
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.