SafePrompt MCP server

• Registry namedev.safeprompt/mcpverified in the MCP registry

The registry name sits under safeprompt.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-29
• Tools2
• Server calls itselfsafeprompt
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 76 ms.

• Its tools do every use case we checked: screen user messages before a chatbot acts on them; check retrieved documents before an agent reads them; flag injected instructions in tool output before use.
• Checked on 5 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
• What an agent can do with it3 of 3 use cases
• Use233 npm downloads a week2 GitHub stars
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer74 ms
• Space in an agent's context≈ 443 tokensthe definitions of all its tools (2), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• validate_prompt

  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…

• validate_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.