Agent skill · Audited from source

Mcp Setup

skill · vellum-ai/vellum-assistantMIT licenceAudited 14 Oct 2026 · source 19bc86343b63

★ 1,425pushed 1 day ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 19bc86343b63 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Add, authenticate, list, and remove MCP (Model Context Protocol) servers — connect any external tool or service that publishes an MCP endpoint to the assistant

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Mcp Setup (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/mcp-setup

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium5 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS5
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
  • Source foldervellum-ai/vellum-assistant/skills/mcp-setupThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Add, authenticate, list, and remove MCP (Model Context Protocol) servers — connect any external tool or service that publishes an MCP endpoint to the assistant

---
name: mcp-setup
description: Add, authenticate, list, and remove MCP (Model Context Protocol) servers — connect any external tool or service that publishes an MCP endpoint to the assistant
compatibility: "Works on both the Vellum desktop app (local daemon) and the Vellum web app (platform-hosted). Auth flow differs by environment."
metadata:
  emoji: "🔌"
  vellum:
    category: "integrations"
    display-name: "MCP Setup"
---

Configure MCP servers to give the assistant access to any external tool or service that publishes an MCP endpoint.

**DO NOT** run exploratory commands. Do not check available CLI commands, search for bun/npx/node, or investigate transport types. Follow the steps below exactly and stop when done. (Looking up a service's MCP endpoint URL in its own documentation is allowed when the service is not in the recipe table, per Step 3.)

## When to Use

USE THIS SKILL WHEN:

- User asks to connect any external tool or service via MCP
- User asks "what MCP servers / integrations do I have?"
- An MCP tool returns an auth error → run `assistant mcp auth <name>`
- User wants to disconnect an integration

## Prefer Native OAuth Integration (check this first)

Many services have built-in OAuth integrations that are simpler and more reliable than MCP. Before setting up MCP, check whether the service already has a native OAuth provider:

```
assistant oauth providers list
```

If the service appears in that list, connect it natively instead of using MCP:

```
assistant oauth connect <provider>
```

**Only use MCP when:**

- The service is not in `assistant oauth providers list`
- The user explicitly asks to use MCP for a specific service
- The native OAuth integration fails or lacks features the user needs

## Step 1 — Detect your environment

**Before doing anything else**, determine which environment you are in.

Try `host_bash`:

```
echo "desktop ok"
```

- If it succeeds → you are on the **desktop app**. Use `host_bash` for all commands, including `auth` (opens a local browser).
- If it is unavailable → you are on the **web app** (or a cloud-hosted session). Use `bash` for all commands, including `auth` (the platform handles the browser redirect).

Both environments fully support MCP. The only difference is which tool runs the commands.

## Step 2 — Check the recipe table

**Check this table before doing anything else.** If the service is listed, run the command shown and do nothing else — no exploration, no checking available commands, no looking up documentation.

| Service         | Command                                                                                | After?                          |
| --------------- | -------------------------------------------------------------------------------------- | ------------------------------- |
| Context7 (docs) | `assistant mcp add context7 -t streamable-http -u https://mcp.context7.com/mcp -r low` | Done — no auth needed           |
| Linear          | `assistant mcp add linear -t streamable-http -u https://mcp.linear.app/mcp`            | Run `assistant mcp auth linear` |
| Figma           | `assistant mcp add figma -t streamable-http -u https://mcp.figma.com/mcp`              | Run `assistant mcp auth figma`  |

If the service is not in this table, go to Step 3.

## Step 3 — Unknown service

Find the MCP endpoint URL in the service's documentation, then run:

```
assistant mcp add <name> -t streamable-http -u <url>
```

Then run `assistant mcp list`. If it shows `! Needs authentication`, run `assistant mcp auth <name>`.

- On **desktop** → run via `host_bash` (opens the local browser).
- On **web app** → run via `bash` (the platform handles the browser redirect).

---

## Reference: All Commands

Run `list`, `add`, `remove`, and `reload` via `bash` on both environments. Run `auth` via `host_bash` on desktop, or via `bash` on the web app.

### List servers

```
assistant mcp list
assistant mcp list --json   # machine-readable output
```

Shows each server's connection status, transport, and URL/command. Status indicators:

- `✓` Connected
- `✗` Error
- `!` Needs authentication

### Add a server

```
assistant mcp add <name> -t <transport> -u <url>
```

Transport types:

- `streamable-http` — most modern remote servers (use this by default)
- `sse` — legacy remote servers
- `stdio` — local process: use `-c <command>` and `-a <args...>` instead of `-u`

Examples:

```
assistant mcp add linear -t streamable-http -u https://mcp.linear.app/mcp
assistant mcp add context7 -t streamable-http -u https://mcp.context7.com/mcp
assistant mcp add local-db -t stdio -c npx -a -y @my/mcp-server
```

### Authenticate (OAuth)

```
assistant mcp auth <name>
```

- On **desktop** → run via `host_bash` (opens the user's local browser for OAuth login).
- On **web app** → run via `bash` (the platform handles the browser redirect and saves tokens).

Tokens are saved automatically. Use when:

- `assistant mcp list` shows `! Needs authentication`
- An MCP tool call fails with an auth/token error
- Setting up a new OAuth-protected server for the first time

### Remove a server

```
assistant mcp remove <name>
```

Removes config and cleans up stored OAuth credentials.

### Reload

```
assistant mcp reload
```

Manually signals the assistant to reconnect all MCP servers from disk. Normally not needed — the assistant detects changes automatically after `add`, `remove`, and `auth`. Use this only if a server's tools aren't appearing after ~10 seconds.

## Advanced Configuration

`mcp add` covers the common cases. For stdio environment variables, edit `$VELLUM_WORKSPACE_DIR/mcp.json` under `mcpServers.<name>.env`. Auth headers for remote servers go through `assistant mcp add -H` or the settings UI, not `mcp.json`.

## SKILL COMPLETE WHEN

Match the completion condition to the task:

- **Add / authenticate:** the server appears in `assistant mcp list` with status `✓ Connected` and the user confirms its tools are available in the conversation.
- **Lis

Excerpt, first 6,001 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 19bc863

Download folder ↗
git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

The author documents no install command, so this uses the repository directly. Our verdict covers commit 19bc86343b63 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/mcp-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/mcp-setup/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/mcp-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/mcp-setup/)

Questions about Mcp Setup

What does the Mcp Setup skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Mcp Setup safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Mcp Setup access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (19bc86343b63), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.