Prompt Rejector MCP (revsmoke/promptrejectormcp) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 11 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
74/100

Prompt Rejector MCP

Protects AI agents from prompt injection attacks, jailbreak attempts, and common web vulnerabilities by screening untrusted input through semantic LLM analysis and static pattern matching.

→ revsmoke/promptrejectormcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

revsmoke

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
1 flow detected: GITHUB_TOKEN. We can’t prove the destination matches the brand the credential belongs to.
⚠️
Known vulnerabilities in dependencies: 1 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 7 credentials: ANTHROPIC_API_KEY, CANARY_HMAC_SECRET, GEMINI_API_KEY, GITHUB_TOKEN, HF_TOKEN, NVD_API_KEY, PATTERN_INTEGRITY_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes11 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

check_prompt

Check a user prompt for injection attacks and traditional vulnerabilities (XSS, SQLi). Use this before processing any untrusted user input.

scan_skill

Scan a SKILL.md file for security vulnerabilities including prompt injection, malicious tool usage, data exfiltration attempts, and social engineering. Use this before installing any third-party skills.

list_patterns

List detection patterns from the pattern library. Optionally filter by category.

update_vuln_feeds

Scan NVD and GitHub Advisory databases for new vulnerabilities and generate candidate detection patterns. Candidates are staged for review before activation.

verify_pattern_integrity

Verify the integrity of the pattern library by checking file hashes against the manifest and validating the HMAC signature.

scan_mcp_tool

Lint an MCP tool descriptor for tool-poisoning signals (imperative override language, hidden Unicode) and compute a canonical SHA-256 hash; reports descriptor drift when a priorHash is supplied.

check_lethal_trifecta

Analyze an agent/skill capability set for the lethal trifecta (private-data read + untrusted-content fetch + external egress).

query_cve

Unified read across NVD, OSV, GHSA, KEV, and ATLAS feeds for AI-relevant CVEs.

deploy_canary

Issue a canary token to embed in memory/RAG context for later echo-detection.

verify_canary

Check provided content for echoes of previously-issued canary tokens (memory/RAG poisoning signal).

taste_test

Detonate a suspect prompt in a dual-agent sandbox (Taster + Monitor) and return the Monitor's verdict on observed intent.

// known CVEs in dependencies1 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.25.3GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEY
configCANARY_DEFAULT_TTL_SECONDS
🔐 secretCANARY_HMAC_SECRET
configCORS_ORIGIN
🔐 secretGEMINI_API_KEYecho "=your_key_here" > .env
🔐 secretGITHUB_TOKENGHSA GraphQL v1.1.0 securityVulnerabilities query with ecosystem filter — richer metadata than REST, requires
🔐 secretHF_TOKEN
🔐 secretNVD_API_KEYyour_nvd_key
🔐 secretPATTERN_INTEGRITY_SECRETFalls back to when unset
configSTART_MODE
configTASTE_TESTER_ENABLED
configTASTE_TESTER_MAX_TOKENS
configTASTE_TESTER_MAX_TURNS
configTASTE_TESTER_MODELclaude-opus-4-7
configTASTE_TESTER_TIMEOUT_MS
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

11/11 tools missing one or more hints — check_prompt (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); scan_skill (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_patterns (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

2 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.25.3 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/revsmoke/promptrejectormcp?variant=verified)](https://m8ven.ai/mcp/revsmoke/promptrejectormcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 2f3a83c266009afa84cc235c43abd7db3d7e6fe3
code hash: da3b105048429fec79e729d9b85ea010ca04411572e8ee9ad5d859cd3b0c3ff2
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client