superFetch MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP bind address | 127.0.0.1 |
| PORT | No | HTTP server port (1024-65535) | 3000 |
| API_KEY | No | Adds a static bearer token and enables X-API-Key header | |
| AUTH_MODE | No | static or oauth. Auto-selects OAuth if OAUTH_ISSUER_URL, OAUTH_AUTHORIZATION_URL, OAUTH_TOKEN_URL, or OAUTH_INTROSPECTION_URL is set | auto |
| CACHE_TTL | No | Cache TTL in seconds (60-86400) | 3600 |
| LOG_LEVEL | No | Logging level (debug enables verbose logs) | info |
| USER_AGENT | No | User-Agent header for outgoing requests | superFetch-MCP/2.0 |
| ALLOW_REMOTE | No | Allow non-loopback binds (OAuth required) | false |
| ACCESS_TOKENS | No | Comma/space-separated static bearer tokens | |
| ALLOWED_HOSTS | No | Additional allowed Host/Origin values | |
| CACHE_ENABLED | No | Enable response caching | true |
| OAUTH_CLIENT_ID | No | Client ID for introspection | |
| OAUTH_TOKEN_URL | No | Token endpoint | |
| TOOL_TIMEOUT_MS | No | Overall tool timeout in ms (1000-300000) | 50000 |
| OAUTH_ISSUER_URL | No | OAuth issuer | |
| OAUTH_RESOURCE_URL | No | Protected resource URL | |
| OAUTH_CLIENT_SECRET | No | Client secret for introspection | |
| OAUTH_REVOCATION_URL | No | Revocation endpoint | |
| TRANSFORM_TIMEOUT_MS | No | Worker transform timeout in ms (5000-120000) | 30000 |
| OAUTH_REQUIRED_SCOPES | No | Required scopes (comma/space separated) | |
| OAUTH_REGISTRATION_URL | No | Dynamic client registration endpoint | |
| OAUTH_AUTHORIZATION_URL | No | Authorization endpoint | |
| OAUTH_INTROSPECTION_URL | No | Introspection endpoint | |
| TRANSFORM_METADATA_FORMAT | No | Raw markdown metadata format (markdown or frontmatter) | markdown |
| OAUTH_INTROSPECTION_TIMEOUT_MS | No | Introspection timeout (1000-30000) | 5000 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch-urlA | Web Content Extractor Fetch public webpages and convert HTML to clean Markdown.
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| get-help | Return Fetch URL server instructions: workflows, cache usage, task mode, and error handling. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| fetch-url-mcp-instructions | Guidance for using the Fetch URL MCP server. |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'fetch-url' has a clearly defined and distinct purpose of fetching web content and converting it to Markdown.
The single tool name 'fetch-url' follows a clear verb_noun pattern, and with only one tool, consistency is inherently perfect. There are no other tools to compare against, so no inconsistencies can exist.
A single tool is too few for a server named 'superFetch MCP Server', which implies a broader or more comprehensive fetching capability. While the tool is well-described, the server's scope feels thin and limited with only one operation, making it borderline inadequate for typical agent workflows.
For a web content extraction server, there are significant gaps in the tool surface. It lacks operations like listing fetched content, managing caches, handling different content types beyond HTML, or providing metadata about fetched URLs. The single tool covers only the core fetch operation, leaving agents with dead ends for related tasks.