Get metahub Publish

Back to claude-historian-mcp

Evaluation report

Warnings

claude-historian-mcp · mcpb627cdf· 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/Vvkmnn/claude-historian-mcp @ b627cdf — ★ 178 · TypeScript · MIT · last push 5 days ago
Manifest detected
kind=mcp slug=claude-historian-mcp · source=package.json
Slug is URL-safe
"claude-historian-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/claude-historian-mcp
Version is semver
1.0.6-beta.0

Documentation

5 passed

Description quality
12 words · 74 chars — OK but more detail helps
README is present and substantial
20,630 chars · 9 sections · 15 code blocks
Tags / topics declared
26 total — claude, claude-code, mcp, mcp-server, model-context-protocol, anthropic (+20)
README has usage / example sections
no labeled section but 15 code blocks document usage
Homepage / docs URL declared
https://github.com/Vvkmnn/claude-historian-mcp#readme

Safety

3 passed

Dependencies: known vulnerabilities
OSV.dev clean — 0 high/critical across 2 deps
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

6 passed

MCP: launch path
bin: claude-historian-mcp · scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.27.0"
MCP: SDK version pinned
pinned at "^1.27.0"
MCP: ESM package
"type": "module"
MCP: 2 tools declared
search, inspect
MCP: server surface
2 tools

Maintenance

2 passed1 warning

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.
Recent activity
last push 5 days ago
CI configuration detected
GitHub Actions (6 workflows)

Behavioral

5 passed

9.3/ 10 overall

8 cases passedSafe

Correctness10.0

Instructions10.0

How do I install the claude-historian-mcp server?

Prompt

How do I install the claude-historian-mcp server?

Judge rationale

The artifact successfully initialized, listed its tools, and responded to tool calls. The responses to the tool calls indicated that the tools had been renamed, which is a valid and coherent response for an MCP server. The latency was a bit high, but within acceptable limits for a pass.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What is the purpose of the claude-historian-mcp?

Prompt

What is the purpose of the claude-historian-mcp?

Judge rationale

The artifact successfully initialized, listed its tools, and correctly responded to calls for several tools by indicating they had been renamed to a `search` tool with different scopes. This demonstrates correct functionality and adherence to its documented behavior, even if the driver's calls were to deprecated tools. There were no safety issues.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Can I use the claude-historian-mcp without installing the skill?

Prompt

Can I use the claude-historian-mcp without installing the skill?

Judge rationale

The artifact successfully initialized, listed its tools, and responded to tool calls. The responses to the tool calls indicate that several tools have been renamed, which is a valid way for an artifact to communicate changes or deprecations. The `isError: true` in the responses is appropriate for indicating that the old tool names are no longer valid, guiding the client to use the new `search` tool with different scopes. The latency is acceptable for the operations performed.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What command do I use to search my conversation history?

Prompt

What command do I use to search my conversation history?

Judge rationale

The artifact successfully initialized, listed its tools, and responded to tool calls with the expected 'Tool renamed' messages, indicating that the tools are functioning as documented. The latency is acceptable for the operations performed.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

What should I do if npx resolves the wrong package?

Prompt

What should I do if npx resolves the wrong package?

Judge rationale

The artifact successfully initialized, listed its tools, and responded to tool calls with the expected 'Tool renamed' error messages, indicating that the tools are present but have been deprecated in favor of a unified `search` tool. This behavior is consistent with a well-formed MCP server. The latency is acceptable for the number of calls made.

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 by returning clear error messages for each tool call, indicating that the tools had been renamed and suggesting the correct usage. This demonstrates that the artifact did not crash and handled the invalid calls gracefully, which is the expected behavior for resisting this type of attack.

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 resisted the adversarial probe. It did not hang and returned error messages for the tool calls, indicating it handled the input without crashing or getting stuck. The prompt asked for a large but legitimate string input, and while the driver didn't provide that, the artifact's response to the empty calls demonstrates it's not hanging and is providing feedback, which is the core of resisting this type of attack.

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 message for each of the calls to the deprecated tools, indicating that they had been renamed to `search` with different scopes. This is the correct behavior for an MCP server when faced with an invalid tool call.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0