wiring-sbx-mcp-servers

Register Model Context Protocol servers on the host with sbx mcp and expose them to sandboxes through the built-in MCP gateway — registration, OAuth, static vs dynamic mode, and Cedar MCP policy. Use when adding an MCP server to a sandbox, deciding between --static-mcp and dynamic discovery, wiring OAuth credentials for a remote server, or writing a governance policy for MCP tool calls.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable reference with concrete commands and clear sequencing; the main gaps are the absence of explicit validation feedback loops for destructive management operations and no progressive split into reference files.

Suggestions

Add an explicit validate-after-step checkpoint (e.g., run `sbx mcp auth status <server>` or `sbx mcp ls` and confirm the expected state) for destructive operations like `sbx mcp rm` and `sbx mcp auth rm`.

Consider splitting the Cedar policy reference and the gateway-tools table into one-level-deep reference files (e.g., `references/cedar-policy.md`) with clearly signaled links from SKILL.md to improve progressive disclosure.

Add a short "verify it worked" line after the OAuth registration flow, since the skill itself notes there is no error to tell you authorization didn't happen.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich with no padding or explanations of concepts Claude already knows; it assumes competence, and time-sensitive version/date info is isolated in a "Last verified" section rather than penalizing the prose.	5 / 5
Actionability	Concrete commands and flags throughout (`sbx mcp add`, `--static-mcp`, `sbx mcp load`, `sbx secret set`, `sbx mcp auth`), copy-paste console examples, and tables of gateway tools cover the common cases fully.	5 / 5
Workflow Clarity	Sections are clearly sequenced (register → choose mode → authorize → manage → policy) with guardrails in a Traps section and verification commands (`auth status`, `ls`), but the destructive registration/token-removal operations lack explicit validate-then-proceed feedback loops, capping it just below the top.	4 / 5
Progressive Disclosure	Well-organized with clear headers and tables in a single cohesive file, but at ~210 lines all content is inline with no one-level-deep reference files split out, so it falls short of the top anchor's clear overview-plus-references structure.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that answers both what and when with concrete triggers and a clearly distinct niche; only minor room for more colloquial trigger phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — "Register Model Context Protocol servers", "expose them to sandboxes through the built-in MCP gateway", "registration, OAuth, static vs dynamic mode, and Cedar MCP policy" — with comprehensive coverage of the skill's scope.	5 / 5
Completeness	It explicitly answers both what (register/expose MCP servers via the gateway, with OAuth, modes, and Cedar policy) and when (concrete "Use when..." trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	The "Use when" clause covers natural triggers ("adding an MCP server to a sandbox", "wiring OAuth credentials", "writing a governance policy") but the phrasing leans technical and omits looser synonyms a user might say, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The sbx-specific host-registration-vs-sandbox-gateway framing carves a clear niche with distinct triggers and minimal overlap risk against generic MCP skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: slurpyb/sbx-agent
Path: skills/wiring-sbx-mcp-servers/SKILL.md
Commit: cd8f798

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.