Promptrejectormcp - install, status & alternatives [2026]

01 · Install Promptrejectormcp

before you install - you'll need

Set TYPESAFE_API_KEY, GEMINI_API_KEY, AI_CONFIG_PATH, API_PROTOCOL, TLS_CERT_FILE, TLS_KEY_FILE 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.

What you can build

With this server connected, an agent can scan skill content and its capabilities/model references, check tool descriptions and nested schema text for poisoning, evaluate private-data access, untrusted input and external egress together, and run an opt-in Taster/Monitor analysis using mocked tools.

Capability map

Tools grouped from the project's README - what Promptrejectormcp lets an agent do.

read & search

3 tools - e.g. Browse detection patterns; Search the configured vulnerability sources; /v2/patterns

list_patterns · query_cve · GET

Check

2 tools - e.g. Screen a prompt; Evaluate private-data access, untrusted input and external egress together

check_prompt · check_lethal_trifecta

Scan

2 tools - e.g. Scan skill content and its capabilities/model references; Check tool descriptions and nested schema text for poisoning

scan_skill · scan_mcp_tool

Verify

2 tools - e.g. Check pattern hashes/signatures; Check content for a canary echo

verify_pattern_integrity · verify_canary

Taste

1 tool - e.g. Run an opt-in Taster/Monitor analysis using mocked tools

taste_test

update

1 tool - e.g. Refresh advisory feeds and draft patterns for review

update_vuln_feeds

Deploy

1 tool - e.g. Create a memory/RAG canary token

deploy_canary

create & write

1 tool - e.g. /v2/check-prompt

POST

Latest releases

v1.2.0 · 2026-09-21

Highlights · Active TypeSafe Jev analysis: focused security judgments for prompts, skills, MCP tool descriptions, agent capabilities and model references, with bounded caching and request accounting. · Choose your…

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 #95 of 216 actively-maintained security servers as of 2026-09-30.
release cadence: 1 release in the last 90 days (latest 2026-09-21)
registry: io.github.revsmoke/promptrejectormcp (active, first published 2026-01-27 · 2 versions)
packages: npm:prompt-rejector

06 · Promptrejectormcp FAQ

Is Promptrejectormcp still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-21 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can Promptrejectormcp do?

With this server connected, an agent can scan skill content and its capabilities/model references, check tool descriptions and nested schema text for poisoning, evaluate private-data access, untrusted input and external egress together, and run an opt-in Taster/Monitor analysis using mocked tools.

How do I install Promptrejectormcp?

Run `npx -y prompt-rejector`. The README documents 6 environment variables (TYPESAFE_API_KEY, GEMINI_API_KEY, AI_CONFIG_PATH…) to set first. Set TYPESAFE_API_KEY, GEMINI_API_KEY, AI_CONFIG_PATH, API_PROTOCOL, TLS_CERT_FILE, TLS_KEY_FILE 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.

Pairs well with

Servers that cover what Promptrejectormcp doesn't - only shown when the pairing reason fits the companion.

More security MCP servers · X (Twitter) · Royal MCP · Hush · Janee · Agent Wormhole

More TypeScript MCP servers · Tyrekick · Rigour · TensorFeed x402 Base Reader · Claude Prompt Optimizer · Gemini MCP · see all