Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
71
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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.
The workflow documentation indicates runtime reads from user-specified external server targets (e.g., HTTP/S URLs in `fastmcp list` / `fastmcp call`), which can cause arbitrary outsider-authored free text (web/MCP server responses) to be ingested into the agent’s LLM context.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill documentation allows running npx commands as stdio targets (e.g., "npx -y @modelcontextprotocol/server-github" and "npx -y @mcp/server"), which fetch and execute remote npm packages at runtime and therefore execute external code under the agent's control.
c9cf237
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.