Universal Web Retrieval MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAVILY_API_KEY | No | Tavily keyed mode; absent → official keyless (X-Tavily-Access-Mode: keyless) | |
| ANYSEARCH_API_KEY | No | AnySearch keyed mode; absent → official keyless | |
| WEB_RETRIEVAL_TIMEOUT | No | Overall chain deadline in seconds (default 45) | 45 |
| WEB_RETRIEVAL_LOG_LEVEL | No | Log level; logs go to stderr (stdout is MCP JSON-RPC) | WARNING |
| WEB_RETRIEVAL_MAX_RESULTS | No | Cap for web_search.limit (default 20) | 20 |
| WEB_RETRIEVAL_DDGS_TIMEOUT | No | DDGS overall timeout in seconds (default 15s) | 15 |
| WEB_RETRIEVAL_TAVILY_TIMEOUT | No | Tavily read timeout in seconds (default 20s) | 20 |
| WEB_RETRIEVAL_ANYSEARCH_TIMEOUT | No | AnySearch read timeout in seconds (default 20s) | 20 |
| WEB_RETRIEVAL_EXTRACT_CHAR_LIMIT | No | Max fetched-content chars (default 15000) | 15000 |
| WEB_RETRIEVAL_TAVILY_CONNECT_TIMEOUT | No | Tavily connect timeout in seconds (default 5s) | 5 |
| WEB_RETRIEVAL_ANYSEARCH_CONNECT_TIMEOUT | No | AnySearch connect timeout in seconds (default 5s) | 5 |
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 |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchA | Web search through a configurable provider chain with automatic failover. Two modes: |
| web_fetchA | Fetch one URL's page content as Markdown with automatic provider failover (default: AnySearch -> Tavily -> DDGS.extract; operators can reorder the chain with UWR_FETCH_CHAIN). Auth is automatic (keyed when a key is configured, else official keyless). Accepts a single url string, or urls array (max 5) for batch. |
| list_providersA | List every provider this server knows: capabilities (search/fetch), whether it is usable right now (configured / key present), whether it is enabled, and its 1-based position in each active chain. Also reports the active search mode (failover/fanout), the fan-out fan width/grace, and the fetch policy (private-network access, block-page detection, extract limit). Never returns key values. Use it to decide what to pass in web_search/web_fetch |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct action on a distinct resource: search the web, fetch a URL, and introspect the provider configuration. The `providers` parameter explicitly cross-references web_search/web_fetch with list_providers, so the boundary between 'use a provider' and 'inspect providers' is unambiguous.
All three names follow a consistent snake_case verb_noun pattern (web_search, web_fetch, list_providers). The prefix/verb split is predictable and unambiguous across the set.
Three tools is a tight, well-scoped surface for a retrieval server: search, fetch, and configuration introspection. There is no filler or redundant tool, and the provider-chain complexity is absorbed into parameters rather than fragmented into extra tools.
The core retrieval lifecycle (discover via search, retrieve content via fetch, inspect/adjust providers) is fully covered. Minor gaps remain, such as no caching/session state or structured extraction beyond raw Markdown, but agents can work around these.