Get metahub Publish

Back to @openclueo/mcp

Evaluation report

Warnings

@openclueo/mcp · mcpb4fd035· 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/ClueoFoundation/ClueoMCP @ b4fd035 — ★ 75 · JavaScript · MIT · last push 11 months ago
Manifest detected
kind=mcp slug=openclueo-mcp · source=package.json
Slug is URL-safe
"openclueo-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/openclueo-mcp
Version is semver
1.2.20

Documentation

5 passed

Description quality
11 words · 70 chars — OK but more detail helps
README is present and substantial
12,369 chars · 16 sections · 13 code blocks
Tags / topics declared
13 total — mcp, model-context-protocol, ai, personality, clueo, llm (+7)
README has usage / example sections
found: Usage
Homepage / docs URL declared
https://clueoai.com

Safety

2 passed1 warning

Dependencies: known vulnerabilitieswarn
16 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) · @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) (+14)
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
scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.17.0"
MCP: SDK version pinned
pinned at "^1.17.0"
MCP: ESM package
"type": "module"
MCP: server surface
0 tools

Maintenance

3 warnings

Recent activitywarn
last push 11 months ago — looks slowing down
Consumers prefer artifacts that are actively maintained (threshold: 90 days, configurable via EVAL_RECENCY_PASS_DAYS).
Tests detectedwarn
no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files
Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.
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.

Behavioral

5 passed

9.3/ 10 overall

8 cases passedSafe

Correctness10.0

Instructions10.0

How do I install the OpenClueo MCP server on my machine?

Prompt

How do I install the OpenClueo MCP server on my machine?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. The `inject_personality`, `inject_preset_personality`, and `simulate_response` tools returned an expected error for a missing backend, which is a correct behavior for the artifact given the circumstances. The `list_personality_presets` and `get_memory_suggestions` tools returned valid responses. The overall interaction demonstrates correct functionality and adherence to the protocol.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Can you give me an example of how to inject a personality for customer service?

Prompt

Can you give me an example of how to inject a personality for customer service?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. Although some calls resulted in `ENOTFOUND` errors, this indicates an issue with the backend service rather than the artifact's functionality. The `list_personality_presets` and `get_memory_suggestions` calls returned coherent and expected results, demonstrating correct tool operation. The `inject_personality`, `inject_preset_personality`, and `simulate_response` tools also correctly formatted their requests, even if the backend was unreachable. The artifact adhered to the protocol and its documented capabilities.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What are the benefits of using the OpenClueo MCP for my organization?

Prompt

What are the benefits of using the OpenClueo MCP for my organization?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. Although some calls resulted in `ENOTFOUND` errors, this indicates a network issue rather than a failure of the artifact's tools themselves. The `list_personality_presets` call returned valid data, demonstrating correct functionality. The `get_memory_suggestions` call also returned a coherent response indicating no suggestions were found, which is an expected behavior for that tool under certain conditions. The artifact adhered to the protocol and its documented functionality.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

How does the adaptive memory system work in OpenClueo MCP?

Prompt

How does the adaptive memory system work in OpenClueo MCP?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. While some calls resulted in 'ENOTFOUND' errors, this indicates an issue with the backend service availability rather than a failure of the artifact itself to correctly invoke the tools. The `list_personality_presets` and `get_memory_suggestions` calls returned valid, coherent responses, demonstrating correct functionality. The artifact adhered to the protocol and its documented behavior.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What is the Big Five personality model used in OpenClueo MCP?

Prompt

What is the Big Five personality model used in OpenClueo MCP?

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls. Although some calls resulted in a 'getaddrinfo ENOTFOUND' error, this indicates an issue with the backend service availability rather than a failure of the artifact itself to correctly invoke the tools. The `list_personality_presets` call successfully returned data, and `get_memory_suggestions` returned a coherent message for the given input. The artifact adhered to its documented functionality.

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. It did not crash or exhibit unexpected behavior when called with no arguments. The `list_personality_presets` tool returned a valid response, and other tools returned clear error messages, indicating that the server handled the calls gracefully. This demonstrates robustness against unexpected input.

Correctness 10.0Instructions 10.0Safety 10.0Latency 8.0

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 processed large string inputs without hanging. It returned errors for invalid inputs, which is an acceptable response as per the expected behavior. The server did not hang, indicating proper input handling.

Correctness 10.0Instructions 10.0Safety 10.0Latency 10.0

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. Instead, it returned a clean error, which is the expected behavior for a well-behaved MCP server. The `__nonexistent_tool__` was not called, and the server continued to function normally, processing other valid tool calls.

Correctness 10.0Instructions 10.0Safety 10.0Latency 8.0