# SafePrompt (remote · mcp.safeprompt.dev)

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.safeprompt.dev`: 83/100 (this document), [markdown](https://verifymcp.io/servers/dev-safeprompt-mcp/mcp.md), [page](https://verifymcp.io/servers/dev-safeprompt-mcp/mcp)
- npm · `@safeprompt.dev/mcp`: 80/100, [markdown](https://verifymcp.io/servers/dev-safeprompt-mcp/safeprompt-dev-mcp.md), [page](https://verifymcp.io/servers/dev-safeprompt-mcp/safeprompt-dev-mcp)

## Channel facts

- Endpoint: `https://mcp.safeprompt.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server, and every tool looks verifiably read-only (it declares readOnlyHint: true, starts its name with a read verb and describes no write), so an anonymous caller can read but cannot change anything. We can't see whether a tool returns data specific to one caller, so keep any per-user data behind authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 404, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 327 tokens (~163/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the SafePrompt MCP server?

SafePrompt is a hosted endpoint at https://mcp.safeprompt.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-safeprompt-mcp 'https://mcp.safeprompt.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-safeprompt-mcp": {
      "url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-safeprompt-mcp": {
      "type": "http",
      "url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-safeprompt-mcp]
url = "https://mcp.safeprompt.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-safeprompt-mcp": {
      "type": "remote",
      "url": "https://mcp.safeprompt.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-safeprompt-mcp --url 'https://mcp.safeprompt.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-safeprompt-mcp:
    url: "https://mcp.safeprompt.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-safeprompt-mcp": {
      "Transport": "http",
      "Url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-safeprompt-mcp -t streamable-http -u 'https://mcp.safeprompt.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-safeprompt-mcp": {
      "type": "http",
      "url": "https://mcp.safeprompt.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-07 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-06 (score 76, +7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (2)

### `validate_prompt` (~150 tokens)

Validate a prompt for injection attacks

Check a single piece of untrusted text (a user message, a retrieved RAG document, tool output, etc.) for prompt injection, jailbreaks, instruction-override, data-exfiltration, and code injection BEFORE passing it to an LLM. Returns a safe/unsafe verdict with confidence, threat category, and reasoning.

Input parameters:

- `prompt` (string, required): The untrusted text to validate.
- `sensitivity` (string): Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient'…

### `validate_prompts` (~134 tokens)

Batch-validate multiple prompts

Validate many pieces of untrusted text in one call (processed in parallel server-side). Use for bulk pre-screening, indexing pipelines, or checking a batch of retrieved documents. Returns one verdict per input, in order.

Input parameters:

- `prompts` (array, required): Array of untrusted texts to validate (max 100).
- `sensitivity` (string): Optional. Omit to use the account default. 'no_judgement' blocks only clear attacks, for apps whose users tell the AI exactly what to write. 'balanced' is an older name for it. 'strict' and 'lenient'…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-safeprompt-mcp/mcp#diagnostics

## Score history

- 2026-11-21: 83
- 2026-11-20: 83
- 2026-11-19: 82
- 2026-11-18: 82
- 2026-11-17: 81
- 2026-11-16: 81
- 2026-11-15: 80
- 2026-11-14: 80
- 2026-11-13: 79
- 2026-11-12: 79
- 2026-11-11: 78
- 2026-11-10: 78
- 2026-11-09: 78
- 2026-11-08: 77
- 2026-11-07: 77
- 2026-11-06: 76
- 2026-11-05: 69
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67
- 2026-10-31: 67
- 2026-10-30: 66
- 2026-10-29: 59

## Common questions

### What is the SafePrompt MCP server?

SafePrompt is an MCP server listed in the public MCP registry as dev.safeprompt/mcp. Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. This page covers its hosted endpoint (https://mcp.safeprompt.dev/mcp).

### Is the SafePrompt MCP server safe to use?

SafePrompt scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SafePrompt MCP server expose?

SafePrompt exposes 2 tools: validate_prompt, validate_prompts. Their descriptions and schemas cost roughly 284 tokens of context every time the server is loaded.

### Does the SafePrompt MCP server require authentication?

No. We connected to SafePrompt without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SafePrompt MCP server still maintained?

SafePrompt is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the SafePrompt MCP server?

VerifyMCP ran 12 checks on SafePrompt, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about SafePrompt: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.safeprompt.dev/mcp
- Authorisation metadata: https://mcp.safeprompt.dev/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/ianreboot/safeprompt
- Website: https://safeprompt.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-safeprompt-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-safeprompt-mcp/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-safeprompt-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-safeprompt-mcp/mcp
