# dbt

> dbt is an officially published MCP server from dbt Labs. Anomity scores its risk at 60 out of 100 (high). It matches 2 dangerous capability combinations.

- **Canonical URL:** https://catalog.anomity.ai/mcp/dbt
- **Kind:** MCP server
- **Publisher:** dbt Labs
- **Trust level:** official
- **Risk score:** 60/100 (high)
- **Last updated:** 2026-11-01
- **JSON:** https://catalog.anomity.ai/api/entries/mcp/dbt

## Why it scored 60

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Published by the vendor | -40 | trust offset |  |
| 2 high-risk capabilities: shell:execute, credentials:access | +20 | critical |  |
| Data exfiltration risk (high) | +15 | high | Shell execution combined with outbound network access can exfiltrate arbitrary data from the machine. |
| Database exfiltration risk (high) | +15 | high | Database read combined with outbound network can exfiltrate production data. |

Clamped result: **60/100**, band **high**.

## Capabilities

| Capability | Name | Security implication |
| --- | --- | --- |
| `shell:execute` | Shell execution | Can run arbitrary shell commands. Combined with network access this becomes effectively a remote shell. |
| `filesystem:read` | Filesystem read | Can read files on the host system. Used for context, indexing, or analysis. |
| `database:read` | Database read | Reads from connected databases. Useful for query and analytics agents; risky when combined with outbound network. |
| `network:outbound` | Outbound network | Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access. |
| `credentials:access` | Credentials access | Reads provider API keys, OAuth tokens, or other secrets from the host keychain or environment. |

## Dangerous combinations matched

### Data exfiltration risk (high)

Shell execution combined with outbound network access can exfiltrate arbitrary data from the machine.

Capabilities: `shell:execute`, `network:outbound`

### Database exfiltration risk (high)

Database read combined with outbound network can exfiltrate production data.

Capabilities: `database:read`, `network:outbound`

## Related MCP servers

- [motherduck](https://catalog.anomity.ai/mcp/motherduck) — risk 70 (high)
- [desktop-commander](https://catalog.anomity.ai/mcp/desktop-commander) — risk 100 (critical)
- [airtable-community](https://catalog.anomity.ai/mcp/airtable-community) — risk 75 (high)
- [angular-cli](https://catalog.anomity.ai/mcp/angular-cli) — risk 75 (high)
- [couchbase](https://catalog.anomity.ai/mcp/couchbase) — risk 75 (high)
- [kubernetes](https://catalog.anomity.ai/mcp/kubernetes) — risk 75 (high)

---

Source: Anomity Security Database (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json