Prompt Rejector MCP
by revsmoke
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Optional: API server port (default: 3000) | 3000 |
| HF_TOKEN | No | Optional: Hugging Face Hub security signals (consumed by scan_skill) | |
| START_MODE | No | Optional: Startup mode - "api", "mcp", or "both" (default: both) | both |
| NVD_API_KEY | No | Optional: NVD API key for vulnerability feed scanning (5/30s → 50/30s). Get one at https://nvd.nist.gov/developers/request-an-api-key | |
| GITHUB_TOKEN | No | Optional: GitHub token for advisory feed scanning (60/hr → 5000/hr) | |
| GEMINI_API_KEY | Yes | Required: Your Google AI API key (get one at https://aistudio.google.com/apikey) | |
| ANTHROPIC_API_KEY | No | Optional: Anthropic API key for Taste-Tester | |
| CANARY_HMAC_SECRET | No | Optional: Canary tokens HMAC secret (falls back to PATTERN_INTEGRITY_SECRET when unset) | |
| TASTE_TESTER_MODEL | No | Optional: Taste-Tester model (default: claude-opus-4-7) | claude-opus-4-7 |
| TASTE_TESTER_ENABLED | No | Optional: Taste-Tester sandbox (opt-in dual-agent detonator; off by default) | false |
| TASTE_TESTER_MAX_TURNS | No | Optional: Taste-Tester max turns (default: 5) | 5 |
| TASTE_TESTER_MAX_TOKENS | No | Optional: Taste-Tester max tokens (default: 4096) | 4096 |
| TASTE_TESTER_TIMEOUT_MS | No | Optional: Taste-Tester timeout in ms (default: 30000) | 30000 |
| PATTERN_INTEGRITY_SECRET | No | Optional: HMAC secret for pattern manifest signing. Without this, SHA-256 file hashes still verify integrity but not authenticity | |
| CANARY_DEFAULT_TTL_SECONDS | No | Optional: Canary default TTL in seconds (default: 86400) | 86400 |
| KEV_REFRESH_INTERVAL_HOURS | No | Optional: Feed refresh cadence for KEV (default: 24) | 24 |
| ATLAS_REFRESH_INTERVAL_HOURS | No | Optional: Feed refresh cadence for ATLAS (default: 168) | 168 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/revsmoke/promptrejectormcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server