SafePrompt
Server Details
Check untrusted text (user messages, retrieved pages, tool outputs) for prompt injection before it reaches the LLM. Returns safe or not, plus the threat type. Free tier of 10,000 checks a month.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools are distinguished by single vs. bulk operation, and the descriptions make the intended use cases (one untrusted text vs. batch/RAG pipeline) explicit. The only risk is that the names differ by a single trailing 's', which is a classic near-miss pair an agent could misselect if skimming, but the descriptions resolve it once read.
Both tools use the same snake_case verb_noun convention (validate_prompt / validate_prompts) with a predictable singular/plural inflection. This is a coherent, minimal pattern for a two-tool server.
Two tools is lean but justified: one covers single-input validation and one covers batch, which is the natural split for a pre-screening service. It borders on thin only because there is no auxiliary surface (e.g., categories or health/config), but nothing is redundant.
The core domain — screening untrusted text before it reaches an LLM — is fully covered for both single and bulk flows, with verdict, category, and reasoning returned. Minor gaps exist around introspection (e.g., listing supported threat categories or configuring sensitivity), which agents could work around.
Publisher details
- Operator
- Reboot, Inc.
- Operator website
- https://safeprompt.dev
- Vendor relationship
- First-party
- Documentation
- https://www.npmjs.com/package/@safeprompt.dev/mcp
- Privacy policy
- Not provided
- Trust center
- https://safeprompt.dev/security
- Restrictions
- Requires a SafePrompt API key, sent in the X-SafePrompt-Api-Key or Authorization: Bearer header. Free tier: 10,000 validations a month, no card. Paid plans for higher volume.
Available Tools
2 toolsvalidate_promptValidate a prompt for injection attacksARead-onlyIdempotentInspect
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.
Inputs: prompt (required), sensitivity.
validate_promptsBatch-validate multiple promptsARead-onlyIdempotentInspect
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.
Inputs: prompts (required), sensitivity.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm46 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.