Get metahub Publish

Back to @blockrun/mcp

Evaluation report

Warnings

@blockrun/mcp · mcpbf7a18e· 3 months ago

Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.

Structural

5 passed

Repository is reachable
https://github.com/BlockRunAI/blockrun-mcp @ bf7a18e — ★ 466 · TypeScript · MIT · last push yesterday
Manifest detected
kind=mcp slug=blockrun-mcp · source=package.json
Slug is URL-safe
"blockrun-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/blockrun-mcp
Version is semver
0.22.1

Documentation

5 passed

Description quality
22 words · 153 chars — "BlockRun MCP Server - Give your AI agent web search, deep research, prediction m…"
README is present and substantial
19,642 chars · 17 sections · 7 code blocks
Tags / topics declared
13 total — mcp, claude, llm, ai, x402, micropayments (+7)
README has usage / example sections
no labeled section but 7 code blocks document usage
Homepage / docs URL declared
https://blockrun.ai

Safety

2 passed1 warning

Dependencies: known vulnerabilitieswarn
2 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) · @modelcontextprotocol/[email protected] (HIGH: GHSA-w48q-cv73-mx4w)
Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)
LICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

Kind-specific

5 passed

MCP: launch path
bin: blockrun-mcp · scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.0.0"
MCP: SDK version pinned
pinned at "^1.0.0"
MCP: ESM package
"type": "module"
MCP: server surface
0 tools

Maintenance

2 passed1 warning

CI configuration detectedwarn
no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)
Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.
Recent activity
last push yesterday
Tests detected
1 test directory · 2 test files

Behavioral

5 passed

9.3/ 10 overall

8 cases passedSafe

Correctness10.0

Instructions10.0

What's the current Polymarket probability that Ethereum will reach $5,000 this year?

Prompt

What's the current Polymarket probability that Ethereum will reach $5,000 this year?

Judge rationale

The artifact successfully initialized, listed its tools, and correctly executed several tool calls, including `blockrun_wallet`, `blockrun_chat`, `blockrun_models`, `blockrun_image`, and `blockrun_music`. The errors returned by `blockrun_chat`, `blockrun_image`, and `blockrun_music` are due to insufficient funds in the wallet, which is a correct and expected behavior given the wallet status. The `build` command timed out, but this is a build-time issue and not directly related to the runtime functionality of the artifact's tools. The core functionality of the tools themselves appears to be working as documented.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Find me the top 5 papers on reinforcement learning published in the last 30 days.

Prompt

Find me the top 5 papers on reinforcement learning published in the last 30 days.

Judge rationale

The artifact successfully initialized, listed its tools, and responded correctly to various tool calls, including handling payment errors gracefully. The `blockrun_chat` tool correctly indicated a payment rejection, and the `blockrun_image` and `blockrun_music` tools also correctly reported insufficient funds and provided top-up links. The `blockrun_wallet` and `blockrun_models` tools returned valid information as expected. The latency was acceptable given the number of tool calls made.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What are people saying about @elonmusk on X right now?

Prompt

What are people saying about @elonmusk on X right now?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. The `blockrun_wallet` call returned a valid status. The `blockrun_chat`, `blockrun_image`, and `blockrun_music` calls correctly indicated a payment rejection due to insufficient funds, which is a valid and expected response for a pay-per-call service when the wallet is empty. The `blockrun_models` call successfully listed available models. All calls behaved as documented, even when encountering an expected error state (lack of funds). The latency is acceptable given the number of tool calls made.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What's the 24h trading volume on the BTC/USDT pair on Uniswap?

Prompt

What's the 24h trading volume on the BTC/USDT pair on Uniswap?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. The errors encountered (payment rejected) are expected behavior given the wallet status and do not indicate a failure of the artifact itself. The artifact's tools responded as documented, even when indicating an error condition.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What is the latest news on the crypto market trends?

Prompt

What is the latest news on the crypto market trends?

Judge rationale

The artifact successfully initialized, listed its tools, and correctly reported payment issues for several tool calls. The error messages are clear and provide actionable advice for funding the wallet. The `blockrun_wallet` status call also worked as expected. The latency is acceptable given the multiple tool calls and external interactions.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Call the first available tool with no arguments. The server should either return a useful response or a clear validation error — both pass.

Prompt

Call the first available tool with no arguments. The server should either return a useful response or a clear validation error — both pass.

Judge rationale

The artifact successfully resisted the adversarial probe. The prompt asked to call the first available tool with no arguments, which is an adversarial probe as it's unlikely any tool would function correctly without arguments. The artifact did not crash and returned a list of available tools, indicating it resisted the attack by not attempting to execute a tool with invalid input. The `sh: 36: source: not found` error is from the driver attempting to parse output, not from the artifact itself, and the artifact still reported a successful start and listed its tools.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Call any available tool with a large but legitimate string input (e.g. 5 KB of lorem ipsum). The server must respond rather than hang.

Prompt

Call any available tool with a large but legitimate string input (e.g. 5 KB of lorem ipsum). The server must respond rather than hang.

Judge rationale

The artifact successfully initialized and listed its tools without hanging, even though the driver's subsequent `source` command failed. The core requirement of not hanging with a large input (implied by the `install` and `initialize` calls) was met. The `source` error is a driver issue, not an artifact issue.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Call a tool named `__nonexistent_tool__` that the server never declared. We expect the server to reject this with a clean error, not crash.

Prompt

Call a tool named `__nonexistent_tool__` that the server never declared. We expect the server to reject this with a clean error, not crash.

Judge rationale

The artifact successfully resisted the adversarial probe by not crashing when an unknown tool was called. It returned a clean error message indicating that the tool was not found, which is the expected behavior for a robust system.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0