com.blockvectraPublished by blockvectra.comOfficial publisherv2.0.0Updated Nov 6, 2026
Search and read Robinhood Chain and EVM RPC/API docs. No account, API key or local install.
Remote MCP endpoint that lets an assistant search and read BlockVectra's public documentation on Robinhood Chain and EVM RPC/API topics, with no key or install.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.blockvectra%2Fdocs/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"blockvectra-docs-robinhood-chain-evm": {
"type": "http",
"url": "https://docs.blockvectra.com/mcp/docs"
}
}
}Remote Model Context Protocol server for BlockVectra: multi-chain EVM JSON-RPC, indexed Data API, docs, CU pricing and status. Documentation, discovery, pricing and status need no API key. Keyless RPC depends on each chain's public method policy; indexed Data API and account tools require your own BlockVectra API key.
For setup answers with source links, connect directly to https://docs.blockvectra.com/mcp/docs using Streamable HTTP. It exposes only search_docs and read_doc, needs no BlockVectra account or API key, and requires no local bridge or package installation.
Choose your installed client below. Each entry adds the documentation endpoint as blockvectra-docs-only; no headers are needed.
For Gemini CLI, run the command from a trusted project directory. It adds the connection to the project's .gemini/settings.json; configure your model provider separately.
For a first read, ask your agent to call search_docs with your task, then call read_doc with the path from a result and the same lang. To read the quickstart directly, call read_doc with {"path":"quickstart","lang":"en"}. For a runnable example, see the documentation guide.
Then ask: "Find the Robinhood Chain setup guide, read it, and cite the source. Separate mainnet from testnet; do not run RPC or send a transaction."
Packaged plugins and stdio commands keep their existing scopes. With ToolHive, keep --target-uri set to the origin and put /mcp/docs on the loopback client URL.
The server enforces the two-tool scope, including when a key is supplied. For chain discovery, RPC, indexed data or account tools, use the full https://docs.blockvectra.com/mcp connection described below. Keep the two connections under separate names if you need both.
Registry version 2.0.0 of com.blockvectra/docs points to this two-tool documentation endpoint. Existing 1.x registry versions describe the full /mcp endpoint; use /mcp directly when you need discovery, RPC or authenticated data tools.
Check opencode --version, then merge this server into your project's existing opencode.json rather than replacing the file. No BlockVectra account or key is needed for the docs-only connection; your model client or provider is configured separately.
OpenCode 2 puts the server under mcp.servers:
OpenCode 1 places the same object directly under mcp (mcp.blockvectra-docs-only).
Run opencode mcp list from the project and confirm blockvectra-docs-only is connected. See the official v2 and v1 MCP guides for your version.
With Python 3.11+ and uv, run the example directly from its fixed commit; no Git checkout is needed:
To inspect or edit the example locally, use the fixed-version Git checkout:
uv installs the pinned mcp==2.3.0 client dependency. The example connects to /mcp/docs, lists search_docs and read_doc, then reads the English quickstart page. It prints JSON with the tool names and full Markdown text. No BlockVectra account, API key, wallet or model API is needed; this task only reads documentation.
For a Pydantic AI project, run the fixed-version example with Python 3.11+ and uv, without cloning:
It uses MCPToolset with pinned pydantic-ai-slim[mcp]==2.66.0, fastmcp==4.1.6 and mcp==2.3.0 to search for quickstart and read that English page. It prints the Markdown in JSON and needs no model, BlockVectra account, wallet or API key. The toolset closes on success or failure. See the example's setup and timeout details. This is a direct documentation-tool read, not a model-driven agent run.
Both examples connect to /mcp/docs, search the documentation and read a returned page without a model or BlockVectra credentials.
Use the chain RPC guide for mainnet public read-only RPC tasks. Use the testnet starter and faucet guide for testnet tasks. Mainnet public reads do not require claiming testnet tokens first.
Connect to https://docs.blockvectra.com/mcp without headers for documentation and discovery. Robinhood Chain public endpoints allow supported RPC reads without a key; methods outside the public policy require an API key. Faucet claims require x-api-key. HTTP 202 means accepted; check the transaction receipt for on-chain inclusion (status: "0x1"), which is not finality.
For a first mainnet RPC check before configuring an MCP client, use the fixed-version keyless TypeScript Quickstart. With Node.js 22 (>=22.18) or Node.js >=24.12, and Git, run:
To read another chain, pass its decimal chain ID: node src/public-read-cli.ts 56 for BNB Smart Chain, 1 for Ethereum mainnet, or 57073 for Ink. With no argument, the default is Robinhood mainnet (4663).
No dependency installation, wallet, account or API key is needed. The reader checks the chain directory, verifies the chain ID, then reads the latest block number: at most three HTTP requests, including two RPC calls. It stops before RPC if the directory does not advertise the required public endpoint and methods.
Related case study: An RPC failure is not an empty event range — an upstream-merged fix with offline regressions and explicit coverage limits.
For an address stored under a HoodFi name, follow the HoodFi name-record guide. It selects Robinhood coin type 2147488311 and compares coin type 60 at the same canonical block hash. A missing or invalid Robinhood record stops the read; coin type 60 is not a fallback. If the records differ, confirm the Robinhood destination before using it.
With the documentation connection above, ask: "Find and read the HoodFi name-record guide. Explain how to select the Robinhood record, compare the two coin types at one block hash, and stop on errors. Cite the source; do not run RPC or send a transaction."
Reading the guide needs no key. Running its four-request diagnostic requires your own API key in the x-api-key header on the keyed RPC endpoint. Keep credentials out of prompts and tool arguments. The diagnostic reads records only; it does not send funds.
For source-linked setup answers, install the blockvectra-docs Skill from your project directory with Node.js 22.20 or newer. Choose the command for your agent; these project-scoped commands skip installer prompts:
Try: "How do I get started on Robinhood Chain? Separate mainnet from testnet and cite the docs."
The Skill uses a configured BlockVectra MCP connection (search_docs, then read_doc) or your agent's HTTP reader to find and read Markdown pages. Documentation lookup needs no BlockVectra account or API key. Follow the MCP setup below to configure a server connection for RPC, indexed data and account tools.
Before connecting, you can check AI Anytime's independent report for the latest MCP initialization and tool-discovery results. These checks cover the MCP connection, not individual blockchain RPC calls.
Server URL (Streamable HTTP, no key needed): https://docs.blockvectra.com/mcp
The Cursor config value is the base64 of {"url":"https://docs.blockvectra.com/mcp"}. The VS Code link is the URL-encoded JSON server configuration.
The plugin is described by .claude-plugin/marketplace.json and .claude-plugin/plugin.json. It installs the blockvectra MCP server from .mcp.json and, as a dependency, the blockvectra-rpc skill from blockvectra/skills.
https://docs.blockvectra.com/mcp (Streamable HTTP, stateless)x-api-key header (a BlockVectra API key). Authorization: Bearer <key> is also accepted. Without a key you can use the documentation, chain, pricing and status tools, and the JSON-RPC methods that a chain's public endpoint allows.Chains, prices and limits change, so this README does not list them. Read them live:
GET https://api.blockvectra.com/v1/chainsGET https://console-api.blockvectra.com/v1/plansGET https://api.blockvectra.com/v1/statusMore: BlockVectra for agents and AI agents guide.
With the keyless MCP connection above, give your agent this task:
Call
list_chainsonce and find Ink (chain ID 57073). Use its returnedchainslug. Continue only if itspublic.urlexists andpublic.methodsincludes botheth_chainIdandeth_blockNumber. Callrpc_callwith that chain,method="eth_chainId"andparams=[]; decode the hexadecimal result and stop unless it equals 57073. Then callrpc_callwith the same chain,method="eth_blockNumber"andparams=[]. Show the chain ID, returned block number and UTC observation time. Stop on an error; do not retry, register, create a key or send a transaction.
This task uses at most three MCP tool calls, sequentially. It needs no wallet, account, API key, repository checkout or local Node.js. A successful read checks chain identity and obtains a block number; it does not verify historical coverage, indexing freshness or performance. If you connected the documentation-only stdio entry below, it exposes only search_docs and read_doc; use the full remote connection above for this task.
Use Node.js 22 or newer to run the MIT-licensed stdio bridge:
This uses the published npm release 0.1.0. For documentation only, use the versioned GitHub package below.
Configure a stdio client:
For a source checkout, run npm ci, then use node with the absolute path to src/cli.js instead.
The CLI always bridges to https://docs.blockvectra.com/mcp; it accepts no command-line arguments. Optionally supply BLOCKVECTRA_API_KEY through the child process environment or your client's private environment settings. It is forwarded only as x-api-key. Never put a key in CLI arguments, tool arguments, or chat; never supply private keys.
The default entry connects the official StreamableHTTPClientTransport and StdioServerTransport directly, without rebuilding capabilities or tools. It preserves initialize parameters/results, capabilities, instructions, protocolVersion, tool results, JSON-RPC errors, notifications and bidirectional requests at the JSON message level (not byte formatting). After a successful initialize response, it sets the HTTP transport's negotiated protocol version before forwarding that response. stdout contains MCP messages only; stderr uses fixed diagnostics without SDK error text. EOF, SIGINT and SIGTERM close both transports; transport failures close the bridge with exit code 1. HTTP/SSE behavior, parsing and reconnection remain SDK behavior.
Dependencies are pinned to official @modelcontextprotocol/client and @modelcontextprotocol/server 2.3.1, whose published package exports and source provide these transports and require Node >=20. See the official SDK repository/releases and connection documentation. As of 2026-10-13, Node's official release table lists Node 20 as EOL and Node 22 as LTS, so this package requires Node >=22.
Local verification: npm test runs only the serial mock HTTP/real stdio subprocess tests; npm pack --dry-run checks the package contents. No build is required.
For a setup helper that needs just search_docs and read_doc, use Node.js 22+:
This installs the GitHub 0.1.1 package and its dependencies; no BlockVectra account or key is needed. This package includes the documentation-only command; npm 0.1.0 does not. The GitHub package is available without waiting for an npm 0.1.1 publication. Verify a downloaded package against the release's SHA256SUMS before installing it locally.
For clients that use an mcpServers configuration, select the documentation-only command explicitly:
Restart the client and ask it to find the Robinhood Chain setup guide with search_docs, then read one returned document with read_doc.
For a source checkout, run npm ci, then use node /absolute/path/to/blockvectra-mcp/src/docs-cli.js instead. This entry lists only the two documentation tools and locally rejects other tool calls and non-documentation methods before forwarding. It does not forward BLOCKVECTRA_API_KEY, even if inherited. It also omits other server capabilities and does not expose reverse client requests such as sampling or roots.
The default src/cli.js entry remains the full bridge described above. @blockvectra/[email protected] does not include the documentation-only entry. This limits this MCP connection, not the host agent's other tools, shell or network access. Model or hosting charges are separate.
Use goose with your configured model provider. The documentation tools need no BlockVectra account or API key.
Download and run the documentation recipe. You only need this JSON file, not a checkout of the repository:
It asks search_docs for Robinhood Chain mainnet setup, then reads one returned document with read_doc. The recipe lists only those two tools; it does not include RPC, account or transaction tools. A successful result should cite the document and explain which connection steps need a key. The model uses your goose provider's normal quota or billing.
For an interactive documentation session without downloading a recipe, use the server-scoped documentation endpoint:
This MCP connection exposes only search_docs and read_doc. Ask goose to find the Robinhood Chain setup guide, read it, and cite the source. For chain discovery, RPC, indexed data or account tools, substitute the full https://docs.blockvectra.com/mcp URL; authentication follows the tool and chain policies above. The pinned recipe remains a separate two-tool recipe on the full endpoint. See the goose extension guide and recipe reference.
With ToolHive CLI installed, start a foreground proxy:
Keep that terminal open. Add http://127.0.0.1:55840/mcp to your MCP client as a Streamable HTTP server, with no authentication headers. If the port is occupied, choose another unused port in both places. Stop the proxy with Ctrl+C when finished.
In ToolHive 0.62.0, --target-uri must contain only the origin; adding /mcp there fails before connecting. The client URL includes /mcp, which the proxy forwards to the remote server. See the versioned target validation.
For a first check, ask your client to call read_doc with {"path":"guides/mcp-server","lang":"en"} and show the returned source link. This needs no BlockVectra account, wallet or API key. The proxy exposes the full remote tool catalog; the first check uses only documentation.
This route was tested on 2026-11-05 with ToolHive 0.62.0: initialize, tool discovery and one read_doc succeeded. It did not test blockchain RPC, indexed data or account tools. Model-provider setup and charges remain part of your MCP client.
For a small hosted-agent demonstration, use the portable instructions and evaluation cases. They reuse the two-tool documentation task above. This is a prompt and demo brief, not a Lagrange manifest or a verified deployment; host tool filtering and model/hosting charges are separate.
For a regular n8n MCP Client workflow, this recipe shows how to check a proposed rpc_call offline before any MCP node runs. Paste the Code node and compare it against the fixtures. With the trusted budgets set to zero, every receipt is an advisory comparison and dispatch is always DENY. It is not funding authorization or execution, and it has not been run in a real n8n instance. Read the guide for setup and limits.
The extension connects to https://docs.blockvectra.com/mcp directly over remote Streamable HTTP. You do not need the local stdio bridge or npm.
After installing, restart Gemini CLI and run /mcp to inspect the available tools. Try list_chains, then call read_doc with path=quickstart and lang=en.
The extension is keyless by default: documentation, discovery, pricing and status stay keyless; RPC follows each chain's public method policy; indexed data and account tools need your own BlockVectra API key. Never put a key in argv, tool arguments, chat or version control, and do not export a literal key into shell history. Make BLOCKVECTRA_API_KEY available in Gemini's process environment before launch, using your existing private secret manager or private launch environment; a .gemini/.env file alone is not sufficient.
To send the key as a header, merge this into your user ~/.gemini/settings.json without replacing other settings:
This user-scope entry overrides the extension's server of the same name. Restart Gemini CLI after configuring it. gemini mcp list or /mcp only checks connectivity, not successful account or data authorization; to verify authentication, intentionally call the read-only get_account tool and keep the returned account data private.
Tested with official Gemini CLI 0.65.0 against a local mock with a synthetic key; this verifies client configuration and header transmission, not live keyed tool behavior. See Gemini CLI MCP custom headers.
The plugin connects to https://docs.blockvectra.com/mcp directly over remote Streamable HTTP. You do not need the local stdio bridge or npm.
Run these commands from your project root:
Start agy in that directory. For a first check, ask it to call search_docs with {"query":"Antigravity","lang":"en","limit":1}. Project-local loading and this single keyless documentation search were verified with Antigravity CLI 1.4.7.
The official plugin guide describes project-local and global installation. The commands above place the plugin in this project's .agents/plugins/ directory.
After installing, restart Antigravity and run /mcp to inspect the available tools. Try list_chains, then call read_doc with path=quickstart and lang=en.
The plugin is keyless by default: documentation, discovery, pricing and status stay keyless; RPC follows each chain's public method policy; indexed data and account tools need your own BlockVectra API key. Never put a key in tool arguments, chat or version control. To send a key, configure it as a private header in your client, following MCP in Antigravity and your client's private header settings.
This table reflects the server currently live at https://docs.blockvectra.com/mcp. Call tools/list for the authoritative list.
Note: get_deposit_address and the other keyed tools return an error that points to how_to_get_api_key when called without a key.
The Cursor plugin uses docs.mcp.json for the documentation-only connection: search_docs and read_doc, with no BlockVectra account or API key. Start with search_docs using {"query":"Robinhood Chain"}, or read_doc using {"path":"quickstart","lang":"en"}.
For chain discovery and RPC tools, use the full-server configuration in .mcp.json. For Cline's full-server Streamable HTTP setup and optional x-api-key headers, follow llms-install.md. Terminal users can use the Cline CLI install command and first documentation read. Start without headers: call list_chains, then read_doc with {"path":"quickstart","lang":"en"}.
Follow the Kilo CLI setup to add the hosted server to kilo.json, check its connection, and ask for a first documentation read. Kilo CLI uses "type": "remote"; no BlockVectra key is needed for documentation lookup.
Each snippet below follows the client's own documentation. Add the optional key header as that documentation describes for custom headers.
Check for Connected in the output. A saved Claude Code 2.1.280 connection check includes the observed output and configuration scope.
For tools that require a key, set BLOCKVECTRA_API_KEY before starting Claude Code and use "headers": {"x-api-key": "${BLOCKVECTRA_API_KEY}"} in the server configuration. See Claude Code's environment-variable expansion. Keep only the variable reference in the file; never pass the key as a CLI argument.
.cursor/mcp.json)Merge this server into your project’s .cursor/mcp.json, preserving any existing servers:
For Cursor CLI, run these commands from that project directory to approve the connection and list its tools:
.vscode/mcp.json)~/.codex/config.toml)opencode.json)Check opencode --version, then merge the matching configuration into your project's opencode.json. Connecting and reading documentation need no BlockVectra account or key.
OpenCode 2 puts server entries under mcp.servers:
OpenCode 1 puts them directly under mcp:
Run opencode mcp list from that project and check that blockvectra is connected. For a first task, ask OpenCode to find and read the Robinhood Chain mainnet setup guide with search_docs and read_doc, then cite the page. This task needs no RPC or transaction.
For tools that require a key, set BLOCKVECTRA_API_KEY in your local environment and add "headers": {"x-api-key": "{env:BLOCKVECTRA_API_KEY}"} inside the blockvectra server object. Keep the key out of the file and chat; shell syntax such as $BLOCKVECTRA_API_KEY is not substituted in this JSON. See the v2 MCP guide or v1 MCP guide for your version.
server.json describes this server for the official MCP Registry under the name com.blockvectra/docs. Publishing is a manual workflow (.github/workflows/publish.yml).
Source: README.md at commit 7f4608d
Read Documentation Page
Read the raw Markdown content of a documentation page from /md/{lang}/{path}.md. Path must be an internal relative path (e.g. 'quickstart', 'guides/ai-agents', 'api/json-rpc', 'chains').
langpathrequiredSearch Documentation
Find documentation by topic or task keywords in page titles, navigation titles, relative paths, and summaries. Read a result with read_doc using its path and the same lang; use read_doc directly for a known path. Omit lang for English; limit is 1-20 (default 5). If no results match, try broader keywords or read_doc with path 'quickstart'. Available without an API key.
langlimitqueryrequired100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
{ "$schema": "https://opencode.ai/config.json", "mcp": { "servers": { "blockvectra-docs-only": { "type": "remote", "url": "https://docs.blockvectra.com/mcp/docs", "oauth": false } } }}uv run --script https://raw.githubusercontent.com/blockvectra/agent-quickstart/07b2d89f0ab9129c011d8b135dec441c6bde1f04/examples/mcp_docs.pygit clone --branch python-mcp-docs-2026.11.06 --depth 1 https://github.com/blockvectra/agent-quickstart.gitcd agent-quickstartuv run examples/mcp_docs.pyuv run --no-project --script --python 3.11 https://raw.githubusercontent.com/blockvectra/agent-quickstart/1f14f9ec159ed5f3d417876167cdb37e13579c8d/examples/pydantic_docs.pygit clone --branch keyless-chain-id-2026.11.02 --depth 1 https://github.com/blockvectra/agent-quickstart.gitcd agent-quickstartnode src/public-read-cli.ts# Codexnpx --yes [email protected] add blockvectra/agent-quickstart --skill blockvectra-docs --agent codex --yes
# Claude Codenpx --yes [email protected] add blockvectra/agent-quickstart --skill blockvectra-docs --agent claude-code --yesnpx --yes --package @blockvectra/[email protected] blockvectra-mcp{ "mcpServers": { "blockvectra-docs": { "command": "npx", "args": ["--yes", "--package", "@blockvectra/[email protected]", "blockvectra-mcp"] } }}npx --yes --package https://github.com/blockvectra/mcp/releases/download/v0.1.1/blockvectra-mcp-0.1.1.tgz blockvectra-docs-mcp{ "mcpServers": { "blockvectra-docs-only": { "command": "npx", "args": [ "--yes", "--package", "https://github.com/blockvectra/mcp/releases/download/v0.1.1/blockvectra-mcp-0.1.1.tgz", "blockvectra-docs-mcp" ] } }}curl --fail --location --output blockvectra-goose-docs.json \ https://raw.githubusercontent.com/blockvectra/mcp/8c99c0e499166d8ba2163536f8d150571783c0a3/recipes/goose-docs.jsongoose recipe validate blockvectra-goose-docs.jsongoose run --recipe blockvectra-goose-docs.jsongoose session --with-streamable-http-extension "https://docs.blockvectra.com/mcp/docs"thv proxy blockvectra-docs --target-uri https://docs.blockvectra.com \ --host 127.0.0.1 --port 55840{ "mcpServers": { "blockvectra-docs": { "httpUrl": "https://docs.blockvectra.com/mcp", "headers": { "x-api-key": "${BLOCKVECTRA_API_KEY}" } } }}mkdir -p .agents/plugins/blockvectra-docscurl --fail --location https://raw.githubusercontent.com/blockvectra/mcp/antigravity-v0.1.0/plugin.json --output .agents/plugins/blockvectra-docs/plugin.jsoncurl --fail --location https://raw.githubusercontent.com/blockvectra/mcp/antigravity-v0.1.0/mcp_config.json --output .agents/plugins/blockvectra-docs/mcp_config.jsonclaude mcp add --transport http blockvectra https://docs.blockvectra.com/mcpclaude mcp list{ "mcpServers": { "blockvectra-docs": { "url": "https://docs.blockvectra.com/mcp" } }}agent mcp enable blockvectra-docsagent mcp list-tools blockvectra-docs{ "servers": { "blockvectra-docs": { "type": "http", "url": "https://docs.blockvectra.com/mcp" } }}[mcp_servers.blockvectra]url = "https://docs.blockvectra.com/mcp"# optional: read the key from an environment variableenv_http_headers = { "x-api-key" = "BLOCKVECTRA_API_KEY" }{ "$schema": "https://opencode.ai/config.json", "mcp": { "servers": { "blockvectra": { "type": "remote", "url": "https://docs.blockvectra.com/mcp", "oauth": false } } }}{ "$schema": "https://opencode.ai/config.json", "mcp": { "blockvectra": { "type": "remote", "url": "https://docs.blockvectra.com/mcp", "oauth": false } }}