# BlockVectra: multi-chain RPC & Data API (remote · docs.blockvectra.com)

Keyless multi-chain EVM JSON-RPC, indexed Data API, docs, CU pricing and status. API key optional.

- Trust score: 68/100 (medium)
- Change this week: −5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-07

> **Recent critical change**: Authorization (2026-10-02). See the changelog below before you install this server.

## Components

- remote · `docs.blockvectra.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-blockvectra-docs/docs.md), [page](https://verifymcp.io/servers/com-blockvectra-docs/docs)

## Channel facts

- Endpoint: `https://docs.blockvectra.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-07.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (send_raw_transaction).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2306 tokens (~153/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (93% of tools); any adoption earns full credit.
- **Tool Safety**: 88/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "rpc_call" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the BlockVectra: multi-chain RPC & Data API MCP server?

BlockVectra: multi-chain RPC & Data API is a hosted endpoint at https://docs.blockvectra.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-blockvectra-docs 'https://docs.blockvectra.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-blockvectra-docs": {
      "url": "https://docs.blockvectra.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-blockvectra-docs": {
      "type": "http",
      "url": "https://docs.blockvectra.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-blockvectra-docs]
url = "https://docs.blockvectra.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-blockvectra-docs": {
      "type": "remote",
      "url": "https://docs.blockvectra.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-blockvectra-docs --url 'https://docs.blockvectra.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-blockvectra-docs:
    url: "https://docs.blockvectra.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-blockvectra-docs": {
      "Transport": "http",
      "Url": "https://docs.blockvectra.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-blockvectra-docs -t streamable-http -u 'https://docs.blockvectra.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-blockvectra-docs": {
      "type": "http",
      "url": "https://docs.blockvectra.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-07 (score 68, +1)

- [security] Tool “get_pricing” rewrote its description, which is the text the model reads
- [security] Tool “list_docs” rewrote its description, which is the text the model reads

### 2026-10-06 (score 67, +1)

- [security] Tool “get_deposit_address” rewrote its description, which is the text the model reads
- [security] Tool “read_doc” rewrote its description, which is the text the model reads

### 2026-10-04 (score 66, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “send_raw_transaction”, which the server declares destructive
- [security] Tool “data_api_get” rewrote its description, which is the text the model reads
- [security] Tool “get_method_info” rewrote its description, which is the text the model reads
- [security] Tool “get_pricing” rewrote its description, which is the text the model reads
- [security] Tool “estimate_usage” rewrote its description, which is the text the model reads
- [security] Tool “read_doc” rewrote its description, which is the text the model reads
- [security] Tool “rpc_call” rewrote its description, which is the text the model reads
- [security] Tool “search_docs” rewrote its description, which is the text the model reads
- [security] Tool “rpc_call” no longer declares itself destructive
- [functional regression] Schema quality: 1807 → 2274
- [functional] Destructive annotations: 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "rpc_call" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
- [functional] Server version: 1.0.0 → 1.2.0
- [functional] New tool “get_deposit_address”
- [cosmetic] “rpc_call” reworded the description of “method”
- [cosmetic] “estimate_usage” reworded the description of “calls_per_day”
- [cosmetic] “estimate_usage” reworded the description of “method”

### 2026-10-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-02 (score 66, +2)

- [critical regression] Authorization: unverified → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_status” rewrote its description, which is the text the model reads
- [security] Tool “rpc_call” rewrote its description, which is the text the model reads
- [security] Tool “rpc_call” is now declared destructive
- [functional] Destructive annotations: All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
- [functional] New tool “get_account”

### 2026-10-01 (score 64, −9)

- [security regression] Authorization: partial → unverified
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1279 → 1648
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: pass → 0
- [functional] New tool “data_api_get”
- [functional] New tool “rpc_call”

### 2026-09-30 (score 73)

First indexed and scored.

## MCP tools (15)

### `read_doc` (~127 tokens)

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').

Input parameters:

- `lang` (string): Published documentation language. Omit for English; unavailable languages return an error.
- `path` (string, required): Internal relative documentation path (e.g. 'quickstart', 'guides/ai-agents', 'api/json-rpc'). Do not include protocol, hostname, query string, fragment, or '..'.

### `search_docs` (~98 tokens)

Search Documentation

Search documentation pages using keywords against page title, relative path, and first-paragraph summary. Returns matching page titles, paths, and summaries.

Input parameters:

- `lang` (string): Published documentation language. Omit for English; unavailable languages return an error.
- `limit` (number): Maximum number of search results to return (1-20, default 5).
- `query` (string, required): Keywords to search for in documentation titles, paths, and summaries.

Output parameters:

- `message` (string)
- `results` (array)

### `list_chains` (~81 tokens)

List Supported Chains

Fetch supported blockchain networks and static parameters from `GET /v1/chains`. `methods.allow` and `methods.deny` support wildcard patterns where `deny` takes precedence over `allow`. `state_window_blocks` indicates the historical state window in blocks for state queries (null when full history is available); `max_logs_block_range` limits log queries.

Output parameters:

- `chains` (array)

### `get_status` (~88 tokens)

Get Service and Network Status

Live operational status and network health from `GET /v1/status`. Confirm chain `status` is 'ok' before calling methods; see `list_chains` for static chain capabilities and method policies. For Data API, `data_status` can be 'ok', 'syncing' (queryable and billed normally, but indexing is lagging behind latest block time), or 'unavailable'.

Output parameters:

- `chains` (array)
- `checked_at` (string)
- `gateway` (object)

### `get_pricing` (~230 tokens)

Get Plans and Pricing

Live prices and plan limits from `GET /v1/plans`. Use before estimating cost or when asked about free credits, rate limits or per-method prices. Units: 1 billing unit = `pricing.cu_per_unit` CU; 1 USD buys `pricing.units_per_usd` units. `method_weights` includes JSON-RPC and Data API CU per call, `push.log` / `push.native_transfer` / `push.token_transfer` per delivered data event, `push.history` per successful history request and `push.address_day` per billable address-day; resolve a method by exact match, then the longest prefix rule ending in `*`, then the `*` row (JSON-RPC only; Data API and push operations have no default). `free.*` values are in billing units; `key_defaults` are per-key CU/s and burst CU. `promo.ends_at` is a sign-up coverage cutoff, not the end of the offer. For a single method's chain support and documentation use get_method_info instead; for projecting cycle costs use estimate_usage instead.

Output parameters:

- `free` (object)
- `key_defaults` (object)
- `method_weights` (array)
- `pricing` (object)

### `estimate_usage` (~202 tokens)

Estimate Usage and Cost

Calculate projected daily and billing cycle Compute Units (CU) and USD costs for planned call volumes across one or more methods, factoring in method weights and free credit allowances from /v1/plans. Also evaluates whether traffic requires multiple API keys under key_defaults. Use this tool for volume budget calculations and capacity planning. For looking up raw system pricing tables, use get_pricing instead. For checking whether a single method is supported on a specific chain, use get_method_info instead. Accepts 'lines' array of {method, calls_per_day} or single 'method' and 'calls_per_day'.

Input parameters:

- `calls_per_day` (integer): Expected daily call volume (non-negative integer). Single-method mode.
- `lines` (array): List of methods and daily call volumes to estimate.
- `method` (string): Exact method name (e.g. 'eth_call', 'eth_getLogs', 'eth_blockNumber', 'data.address_balances'). Single-method mode.

Output parameters:

- `average_calls_per_sec` (number)
- `calls_per_day` (number)
- `cu_weight` (number|null)
- `cycle_cost_usd` (number|null)
- `cycle_cu` (number)
- `cycle_days` (number)
- `daily_cost_usd` (number|null)
- `daily_cu` (number)
- `exceeds_free_quota` (boolean)
- `exceeds_rate_limit` (boolean)
- `free_quota_cu` (number|null)
- `max_calls_per_sec` (number|null)
- `method` (string)
- `quota_percent` (number|null)

### `how_to_get_api_key` (~76 tokens)

How to Get API Key

Get instructions and endpoints for obtaining a BlockVectra API key via preferred programmatic SIWE sign-up or browser handoff, plus authentication header and URL formats for JSON-RPC and Data API.

Input parameters:

- `lang` (string): Documentation language: 'en' for English or 'zh' for Chinese. Defaults to 'en'.

Output parameters:

- `auth_methods` (object)
- `env_var` (string)
- `handoff_instructions` (string)
- `paths` (object)
- `preferred_path` (string)

### `get_method_info` (~195 tokens)

Get Method Information

Inspect a single method's chain-by-chain availability, Compute Unit (CU) weight, price per million calls, and documentation link. Check JSON-RPC method policy and Data API dataset coverage separately. JSON-RPC follows methods.allow and methods.deny from /v1/chains. Data API coverage follows data_features in GET /v1/status, with data enabled in /v1/chains. Pricing comes from /v1/plans. For the full system-wide pricing schedule and rate card, use get_pricing instead. For calculating projected bills for expected call volumes across methods, use estimate_usage instead.

Input parameters:

- `chain` (string): Optional chain slug (e.g. 'robinhood_mainnet'). If specified, only availability for this chain is returned.
- `method` (string, required): Method name (e.g. 'eth_call', 'eth_getBalance', 'debug_traceBlockByNumber', 'data.address_balances').

Output parameters:

- `available_chains` (array)
- `chain` (string|null)
- `cost_per_million_usd` (number|null)
- `cu_weight` (number|null)
- `docs_url` (string|null)
- `method` (string)
- `notes` (string|null)
- `supported` (boolean)

### `explain_error` (~178 tokens)

Explain Error Code or Reason

Lookup error code, reason, or HTTP status in the official error reference catalog. Returns meaning, billing implications (whether the call was billed), retryability, retry delay, recommended agent action, and documentation URL.

Input parameters:

- `code` (number|string): Error code (e.g. -32600, -32005, -32020, or console code string like 'siwe_invalid').
- `http_status` (number): HTTP status code (e.g. 200, 400, 402, 404, 429, 500, 503).
- `lang` (string): Language for explanations: 'en' for English or 'zh' for Chinese. Defaults to 'en'.
- `reason` (string): Error reason slug (e.g. 'invalid_request', 'key_rate_limit', 'insufficient_balance', 'not_found').

Output parameters:

- `count` (number)
- `errors` (array)
- `matched` (boolean)

### `list_docs` (~62 tokens)

List Documentation Pages

List all available documentation pages, relative paths, and titles from the static documentation index, including webhook push subscriptions, signatures, delivery and billing. No API key required.

Input parameters:

- `lang` (string): Published documentation language. Omit for English; unavailable languages return an error.

Output parameters:

- `count` (number)
- `docs` (array)
- `lang` (string)

### `rpc_call` (~255 tokens)

Call JSON-RPC Method

Execute a read-only JSON-RPC 2.0 method on a specified blockchain network using your BlockVectra API key, or via the keyless public endpoint if available on the chain. Write methods (such as 'eth_sendRawTransaction') are not supported in rpc_call; use 'send_raw_transaction' instead. Consult the Ethereum JSON-RPC specification (https://ethereum.org/en/developers/docs/apis/json-rpc/) and the BlockVectra method reference (https://docs.blockvectra.com/en/api/json-rpc/methods/). Requires the 'x-api-key' or 'Authorization: Bearer <key>' HTTP header in your MCP client configuration for full access (keys must not be passed in tool parameters or chat). Returns the raw JSON-RPC response from the server.

Input parameters:

- `chain` (string, required): Target blockchain network slug (e.g. 'robinhood_mainnet'). Must exist in GET /v1/chains.
- `method` (string, required): JSON-RPC 2.0 method name (e.g. 'eth_blockNumber', 'eth_call', 'eth_getLogs'). Write methods are not accepted.
- `params` (array): Optional JSON-RPC parameter array. Defaults to [].

Output parameters:

- `balance_units` (integer): Remaining balance units after this request (only present when balance is known and x-bv-meter: 1 was sent).
- `cu_charged` (integer): Compute Units billed for this request (only present when charged and x-bv-meter: 1 was sent).
- `error` (object|string)
- `help` (object)
- `id` (number|string|null)
- `jsonrpc` (string)
- `message` (string)
- `result`
- `signup_url` (string): Registration and sign-up URL (returned when rate-limited on the public endpoint).

### `data_api_get` (~189 tokens)

Query Data API

Query the BlockVectra Data API for a specified chain and path using your BlockVectra API key. For endpoint schemas and parameter specifications, see the OpenAPI contract at https://docs.blockvectra.com/openapi/data.yaml. Requires the 'x-api-key' or 'Authorization: Bearer <key>' HTTP header in your MCP client configuration (keys must not be passed in tool parameters or chat). Returns the HTTP status and JSON response body.

Input parameters:

- `chain` (string, required): Target blockchain network slug (e.g. 'robinhood_mainnet').
- `path` (string, required): Path after '/v1/data/{chain}/' (e.g. 'status/freshness', 'address/0x.../balances'). Must not start with '/', and cannot contain '..', '//', '?', '#', or '%'.
- `query` (object): Optional URL query parameters as key-value pairs.

Output parameters:

- `_truncated` (boolean)
- `balance_units` (integer): Remaining balance units after this request (only present when balance is known and x-bv-meter: 1 was sent).
- `bytes` (integer)
- `cu_charged` (integer): Compute Units billed for this request (only present when charged and x-bv-meter: 1 was sent).
- `data`
- `error` (string)
- `status` (number)

### `get_account` (~106 tokens)

Get Account Balance and Limits

Get the API key's own balance, Compute Units (CU), rate limits, and key parameters from GET /v1/account using your BlockVectra API key. Free and unbilled. Requires the 'x-api-key' or 'Authorization: Bearer <key>' HTTP header in your MCP client configuration (never pass keys in tool parameters or chat). Returns the account's key_id, plan, balance_units, balance_cu, balance_as_of_age_ms, and key limits.

Output parameters:

- `_truncated` (boolean)
- `balance_as_of_age_ms` (integer)
- `balance_cu` (integer)
- `balance_units` (integer)
- `bytes` (integer)
- `data`
- `error` (string)
- `key` (object)
- `key_id` (string)
- `plan` (string)
- `status` (number)

### `get_deposit_address` (~41 tokens)

Get Deposit Address and Open Networks

Requires an API key. Get your account's dedicated on-chain deposit address and open networks to top up balance; only transfer to the listed networks and tokens.

Output parameters:

- `_truncated` (boolean)
- `address` (string)
- `bytes` (integer)
- `data`
- `deposits_url` (string)
- `error` (string)
- `min_deposit_usd` (string)
- `networks` (array)
- `status` (number)

### `send_raw_transaction` (~146 tokens)

Send Raw Transaction

Broadcast a signed raw transaction to a specified blockchain network via eth_sendRawTransaction. Requires the 'x-api-key' or 'Authorization: Bearer <key>' HTTP header in your MCP client configuration for full access, or uses the keyless public endpoint if permitted on the chain (keys must not be passed in tool parameters or chat). Returns the transaction hash or JSON-RPC error.

Input parameters:

- `chain` (string, required): Target blockchain network slug (e.g. 'robinhood_mainnet'). Must exist in GET /v1/chains.
- `raw_tx` (string, required): Signed raw transaction data as a 0x-prefixed hex string (the RLP-encoded raw transaction).

Output parameters:

- `balance_units` (integer): Remaining balance units after this request (only present when balance is known and x-bv-meter: 1 was sent).
- `cu_charged` (integer): Compute Units billed for this request (only present when charged and x-bv-meter: 1 was sent).
- `error` (object|string)
- `help` (object)
- `id` (number|string|null)
- `jsonrpc` (string)
- `message` (string)
- `result`
- `signup_url` (string): Registration and sign-up URL (returned when rate-limited on the public endpoint).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-blockvectra-docs/docs#diagnostics

## Score history

- 2026-10-07: 68
- 2026-10-06: 67
- 2026-10-04: 66
- 2026-10-03: 67
- 2026-10-02: 66
- 2026-10-01: 64
- 2026-09-30: 73

## Common questions

### What is the BlockVectra: multi-chain RPC & Data API MCP server?

BlockVectra: multi-chain RPC & Data API is an MCP server listed in the public MCP registry as com.blockvectra/docs. Keyless multi-chain EVM JSON-RPC, indexed Data API, docs, CU pricing and status. API key optional. This page covers its hosted endpoint (https://docs.blockvectra.com/mcp).

### Is the BlockVectra: multi-chain RPC & Data API MCP server safe to use?

BlockVectra: multi-chain RPC & Data API scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the BlockVectra: multi-chain RPC & Data API MCP server expose?

BlockVectra: multi-chain RPC & Data API exposes 15 tools: read_doc, search_docs, list_chains, get_status, get_pricing, and 10 more. Their descriptions and schemas cost roughly 2,074 tokens of context every time the server is loaded.

### Does the BlockVectra: multi-chain RPC & Data API MCP server require authentication?

No. We connected to BlockVectra: multi-chain RPC & Data API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the BlockVectra: multi-chain RPC & Data API MCP server still maintained?

BlockVectra: multi-chain RPC & Data API is still listed as active in the MCP registry. We last reached this channel on 7 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://docs.blockvectra.com/mcp
- Repository: https://github.com/blockvectra/mcp
- Website: https://blockvectra.com/en/agents/
- Changelog RSS feed: https://verifymcp.io/servers/com-blockvectra-docs/docs.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-blockvectra-docs/docs.json
- HTML version of this page: https://verifymcp.io/servers/com-blockvectra-docs/docs