CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-mcp-server

Scaffold and wire a brand-new MCP server into this google-docs-mcp hosting platform. Creates the server file, registers it in scopeMap + dispatch router + UserSession + catalog, and optionally clones a reference GitHub MCP repo and ports its tools into this codebase's FastMCP + Zod + UserSession pattern. Use this skill whenever the user mentions adding, creating, or wiring up a new MCP server, integration, or provider in this repo — even when phrased indirectly ("plug in Notion", "expose a new service", "stand up a server for X"). Also use when invoked as `/add-mcp-server <slug> [github-url]`.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is a legitimate scaffolding guide with no concealment, pretexts, impersonation, or covert triggers, but its instruction to clone an arbitrary GitHub repo and port every discovered tool into the codebase without per-tool review is a risky step toward the user, so I classify it as medium under the recall-first override.

Report incorrect finding
Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The only outsider-authored text is the source code, tool descriptions, and docstrings of a user-supplied reference GitHub repo, which the workflow clones and ports at step 3, so this is a selected URL the agent must actively fetch (low, not medium since no issue, PR, or inbox feed is read).

Repository

boarlabsxyz/awesome-mcp

Path

.claude/skills/add-mcp-server/SKILL.md

Audited
Security analysis
Snyk

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.