Anvia MCP Skill
SkillAI & modelsConnect MCP servers to Anvia agents, clients, transports, tool discovery, URL safety, and lifecycle.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Anvia MCP Skill skill
What this skill tells your AI
The instructions your AI receives, as published by anvia-hq/anvia in skills/anvia-mcp/SKILL.md and read by ahel’s review.
Use this skill when the user wants tools from an MCP server: configuring an
McpClient, choosing stdio vs Streamable HTTP, handling version negotiation
and URL safety, grouping servers, or wiring them into an Agent.
Process
- Configure clients (
references/clients.md) — oneMcpClientper server. - Apply the safety rules (
references/safety.md) — especially for HTTP servers. - Run
scripts/check-mcp.shfrom the app root before claiming done.
Minimal slice
import { Agent } from "@anvia/core/agent";
import { McpClient } from "@anvia/mcp";
const counterMcp = new McpClient({
name: "counter",
transport: { type: "stdio", command: "tsx", args: ["./mcp-counter-server.ts"] },
});
const counterServer = await counterMcp.connect();
try {
const agent = new Agent({
id: "agent",
model: agentModel,
instructions: "Use MCP tools for arithmetic and counter updates.",
mcpServers: [counterServer], // the only path for MCP tools — never via skills
maxTurns: 3,
});
for await (const event of agent.stream({ prompt: "Add 8 and 13." })) {
if (event.type === "response") console.log("final:", event.text);
}
} finally {
await counterMcp.close();
}
Output
Prefer stdio for local servers, Streamable HTTP for remote ones. Point to the relevant reference file instead of pasting its contents into chat.
Signals
- GitHub stars
- 50
- Forks
- 6
- Last commit
- Oct 2026
ahel review
K6low
bundled executables the agent is told to run
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Item type
- skill
- Key
anvia-mcp- Source
- github.com/anvia-hq/anvia
Related picks
Skill · mattpocock
The pick for TypeScripttypescript-pro
Skill · jeffallan
The pick for TypeScriptskill-creator
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & models