Website Reader MCP
by AlwIkigai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Host interface for the local uvicorn server to bind to. | 0.0.0.0 |
| PORT | No | Port for the local uvicorn server. | 8001 |
| APP_ENV | No | Application environment name. | local |
| DEV_HTTPS | No | Whether to run the local dev server over HTTPS. | true |
| REDIS_URL | No | Redis connection URL (e.g. Upstash). Required when CACHE_BACKEND=redis or RATE_LIMIT_BACKEND=redis. | |
| MCP_API_KEY | Yes | API key required to authenticate requests to the MCP endpoint (sent via Authorization: Bearer or X-API-Key header). Set a real value; the .env.example default is 'change-me'. | |
| SSL_KEYFILE | No | Path to the local dev TLS private key file. | certs/localhost-key.pem |
| SSL_CERTFILE | No | Path to the local dev TLS certificate file. | certs/localhost.pem |
| CACHE_BACKEND | No | Cache backend: 'memory' for local/single-instance or 'redis' for a shared cache on Vercel. | memory |
| CACHE_ENABLED | No | Enable or disable caching of successful URL fetches at the fetch layer (shared by all tools). | false |
| MAX_HTML_BYTES | No | Maximum number of bytes downloaded while fetching a page. | 2000000 |
| ALLOWED_SCHEMES | No | Comma-separated URL schemes allowed for fetching (only http and https are allowed). | https,http |
| CACHE_MAX_ENTRIES | No | Maximum number of in-memory cache entries (ignored for Redis). | 100 |
| CACHE_TTL_SECONDS | No | How long cached URL fetch responses are kept, in seconds. | 300 |
| MCP_ALLOWED_HOSTS | No | Optional allowlist of Host header values permitted to access /mcp. Empty disables the check. Use '*' to allow any host, exact hosts, subdomain wildcards like *.example.com, or port wildcards like localhost:*. | |
| MAX_RESPONSE_CHARS | No | Maximum number of characters returned in tool output (overridable per call via max_chars). | 12000 |
| RATE_LIMIT_BACKEND | No | Rate limit backend: 'memory' for local/single-instance or 'redis' for shared limits on Vercel. | memory |
| RATE_LIMIT_ENABLED | No | Enable or disable per-client rate limiting on outbound URL fetches. Only cache misses count toward limits. | false |
| SSRF_DNS_RESOLVERS | No | Comma-separated DNS resolvers used for validation. 'system' uses /etc/resolv.conf; others are public resolver IPs. | system,1.1.1.1,1.0.0.1,8.8.8.8,8.8.4.4 |
| MCP_ALLOWED_ORIGINS | No | Optional restriction on browser Origin headers for /mcp requests. Empty disables the check. | |
| RATE_LIMIT_PER_HOUR | No | Maximum URL fetches per client per hour (sustained cap). | 120 |
| RATE_LIMIT_PER_MINUTE | No | Maximum URL fetches per client per minute (burst protection). | 15 |
| REQUEST_TIMEOUT_SECONDS | No | Timeout in seconds for outbound URL fetches. | 12 |
| SSRF_DNS_TIMEOUT_SECONDS | No | Per-query DNS timeout in seconds; resolvers are queried concurrently. | 2 |
| SSRF_DNS_VALIDATION_ENABLED | No | Enable DNS resolution, IP validation and connection pinning to protect against SSRF and DNS rebinding. | true |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues