Promptrejectormcp
A dual-layer security gateway for AI agents and applications. Prompt Rejector protects your AI-powered applications from prompt injection attacks, jailbreak attempts, and traditional web vulnerabilities (XSS, SQLi, Shell Injection) by screening untrusted input before it reaches your agent's control plane. It runs locally over stdio via the published package.
People connecting security tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
VERIFIED ACTIVE
LAST COMMIT 2026-05-18 · ★ 2 · #138 OF 182 MAINTAINED SECURITY · VERIFIED 2026-08-25
ISC · TypeScript servers · how we verify → /methodology
01 · Install Promptrejectormcp
before you install - you'll need
Set GEMINI_API_KEY, START_MODE, KEV_REFRESH_INTERVAL_HOURS, ATLAS_REFRESH_INTERVAL_HOURS, TASTE_TESTER_ENABLED, TASTE_TESTER_MODEL, TASTE_TESTER_MAX_TURNS, TASTE_TESTER_MAX_TOKENS, TASTE_TESTER_TIMEOUT_MS, CANARY_DEFAULT_TTL_SECONDS, GITHUB_TOKEN, NVD_API_KEY before connecting.
Claude Code
claude mcp add revsmoke-promptrejectormcp -- npx -y prompt-rejector Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"revsmoke-promptrejectormcp": {
"command": "npx",
"args": [
"-y",
"prompt-rejector"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license ISC - declared in the repository
npm package prompt-rejector - unscoped; check the name against the project README before installing
registry namespace io.github.revsmoke is GitHub-verified and matches the repo owner
03 · What Promptrejectormcp can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v1.0.2 · 2026-02-09
What's New · Added · Dynamic Pattern Library - File-based pattern CRUD via PatternService with patterns/ directory. Supports two detection modes: simple (any match) and threshold (count/length gating). · Vulnerability…
v1.0.1 · 2026-01-28
Highlights · Automated CI publish: GitHub Actions builds, validates server.json against MCP schema, publishes to npm, then publishes to the MCP Registry via OIDC. · Registry compliance: server.json description…
04 · Who maintains Promptrejectormcp
promptrejectormcp is maintained by revsmoke. It's the only MCP server we track from this author; the repo dates to Jan 2026.
05 · Facts
- repository
- github.com/revsmoke/promptrejectormcp
- category
- security - ranked #138 of 182 actively-maintained security servers as of 2026-08-25.
- registry
- io.github.revsmoke/promptrejectormcp (active, first published 2026-01-27 · 2 versions)
- packages
- npm:prompt-rejector
06 · Promptrejectormcp FAQ
What is Promptrejectormcp?
A dual-layer security gateway for AI agents and applications. Prompt Rejector protects your AI-powered applications from prompt injection attacks, jailbreak attempts, and traditional web vulnerabilities (XSS, SQLi, Shell Injection) by screening untrusted input before it reaches your agent's control plane. It runs locally over stdio via the published package.
Is Promptrejectormcp still maintained?
Yes - as of 2026-08-25, its last commit was 2026-05-18. We re-verify nightly.
How do I install Promptrejectormcp?
Run `npx -y prompt-rejector`. The README documents 12 environment variables (GEMINI_API_KEY, START_MODE, KEV_REFRESH_INTERVAL_HOURS…) to set first. Set GEMINI_API_KEY, START_MODE, KEV_REFRESH_INTERVAL_HOURS, ATLAS_REFRESH_INTERVAL_HOURS, TASTE_TESTER_ENABLED, TASTE_TESTER_MODEL, TASTE_TESTER_MAX_TURNS, TASTE_TESTER_MAX_TOKENS, TASTE_TESTER_TIMEOUT_MS, CANARY_DEFAULT_TTL_SECONDS, GITHUB_TOKEN, NVD_API_KEY before connecting. You can also paste the ready-made client config above.
Does Promptrejectormcp run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Promptrejectormcp
Alternatives to Promptrejectormcp
Maintained security servers if Promptrejectormcp isn't the fit.
- SafeDep Vet MCP Protect your AI agents and IDEs from malicious open-source packages. ★ 1,102 · 2026-08-24
- SonarQube MCP Server Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants. ★ 632 · 2026-08-24
- Decionis MCP Server Fail-closed policy gate for AI agent actions, with local evaluation and native pre-tool hooks. ★ 533 · 2026-08-24
- HOL Guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. ★ 470 · 2026-08-25
- Emisar Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step. ★ 409 · 2026-08-23
- Bradesco MCP server for Bradesco - Pix, Cobrança (boleto), Arrecadação, Extrato (OAuth2 + mTLS) ★ 269 · 2026-08-12
Pairs well with
Servers that cover what Promptrejectormcp doesn't - only shown when the pairing reason fits the companion.
More security MCP servers · Royal MCP · Hush · Janee · Audit
More TypeScript MCP servers · Tyrekick · Rigour · TensorFeed x402 Base Reader · Claude Prompt Optimizer · Gemini MCP · see all