Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add VapiAI/mcp-server --skill skillgit clone --depth 1 https://github.com/VapiAI/mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vapiai/mcp-server/skill)<a href="https://agentmods.dev/skills/vapiai/mcp-server/skill"><img src="https://agentmods.dev/badge/skills/vapiai/mcp-server/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vapiai/mcp-server/skill"><img src="https://agentmods.dev/badge/skills/vapiai/mcp-server/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 18 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00720 |
| Opus 5.5 | $0.00017 | $0.00288 |
| Sonnet 5.5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
vapi scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vapi - AI Voice Assistant Builder
Build AI-powered voice assistants, phone agents, and conversational AI applications with Vapi.
Workflow
1. Check for the Vapi MCP Server
Check whether a Vapi MCP server is connected by discovering tools such as list_assistants. MCP hosts may namespace displayed tool names with the configured server name.
If the server is unavailable, tell the user to configure one of these supported connections in their MCP host:
- Local stdio command:
npx -y @vapi-ai/mcp-server, withVAPI_TOKENset in the server environment - Remote Streamable HTTP:
https://mcp.vapi.ai/mcp, with anAuthorization: Bearer <VAPI_TOKEN>header
Tell the user to reload or restart their MCP host if it requires that after configuration.
2. Confirm Vapi Credentials
If a tool returns an authentication error, tell the user to configure a Vapi API key as VAPI_TOKEN for a local server or as the bearer token for the remote server. Then retry after reloading the connection if required by the host.
3. Build the Voice Assistant
Before creating an assistant, fetch the latest prompt engineering guidelines from the Prompt Guide.
Use these guidelines to craft effective voice assistant prompts based on what the user wants to build.
Available Tools
Assistants
list_assistants- List all assistantsget_assistant- Get assistant detailscreate_assistant- Create new assistantupdate_assistant- Update assistant
Calls
list_calls- List call historyget_call- Get call detailscreate_call- Start outbound call
Phone Numbers
list_phone_numbers- List phone numbersget_phone_number- Get phone number details
Tools (Function Calling)
list_tools- List custom toolsget_tool- Get tool detailscreate_tool- Create tool for API integrationupdate_tool- Update tool
Workflow Examples
User: "I want to build a voice assistant that can schedule appointments"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 79 lines · 43 tokens per session scan A 685ce34e9e18
vapi is a skill published in the GitHub repository VapiAI/mcp-server (58 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 720 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…
td-api-reference
MUST READ before writing TD Python via executepython, setdatcontent, or editdatcontent, and before any heavy build. Parameters, storage, operators, referencing, threading, cook model, heavy-build safety caps.
sanity-singletons
Configure singleton documents in a Sanity Studio using the document.singletons registry. Use when a developer wants a fixed-id document (settings, navigation, footer) edited in place, hidden from the default content list, with no "create new" or "duplicate" affordances — or when migrating a userland singleton…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, the App SDK, and Studios…
tech-specs
To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.