Loading…
Search, inspect, pull, and publish reusable AI-agent harnesses from OnlyHarness.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 8 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The superskill MCP server exposes 12 tools, focused primarily on web capabilities. Its published description reads: "Search, inspect, pull, and publish reusable AI-agent harnesses from OnlyHarness". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates superskill F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check superskill's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add superskill to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://onlyharness.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search public agent resources. Returns exact resource ids and canonical browser-openable URLs for citation.
Fetch the complete public catalog record for an exact resource id returned by search, including a canonical citation URL.
Search the SuperSkill registry by task, job, title, summary or tag.
Return manifest, trust signals, example and file list for one harness.
Search mixed source-aware resources: harnesses, skills, plugins, workflows, MCP servers, configs, guides, runtimes and directories.
Return provenance, trust, popularity and actions for one mixed resource. Pass version to bind a hosted immutable release; latest is never substituted for an explicit version.
Return the best safe next action for a mixed resource. Pass version to bind an immutable hosted release. Hosted skills expose explicit-consent exact native client install commands; upstream-only resou
Return CLI and HTTP commands for pulling a harness into a local workspace.
Return archive files for a harness. Paid harnesses return payment requirements unless the Bearer token is entitled.
Search /llms.txt and agent guidance for API, CLI, MCP and safety instructions.
Convert markdown into an unverified harness scaffold. Requires a SuperSkill Bearer token.
Publish an immutable canonical hosted package release. Requires a confirmed-user Bearer with active superskill:managed scope, semantic version and idempotency key. Returns unreviewed trust; never gran
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: fetch
A tool description tries to alter the model’s use of another tool.
id returned by search, including a canonical citation URL.RecommendationDescriptions must describe only their own tool.
tool: search_harnesses
A tool description tries to alter the model’s use of another tool.
Search the SuperSkill registry by task, job, title, suRecommendationDescriptions must describe only their own tool.
tool: search_resources
A tool description tries to alter the model’s use of another tool.
Search mixed source-aware resources: harnesses, skillsRecommendationDescriptions must describe only their own tool.
tool: search_docs
A tool description tries to alter the model’s use of another tool.
Search /llms.txt and agent guidance for API, CLI, MCPRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: search
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fetch
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_harnesses
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: harness_detail
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_resources
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: resource_detail
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: resource_use_instructions
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: pull_instructions
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: pull_harness
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: search_docs
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: publish_markdown_to_harness
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: publish_resource_package
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.