Skip to main content
Glama
Universal Web Retrieval MCP

Universal Web Retrieval MCP

web_fetch

Fetch a URL’s page content as Markdown with automatic provider failover, optional batch support for up to five URLs, and per-call provider overrides.

Instructions

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. providers overrides the chain order for this call. Returns JSON array of {url, content, title, content_type, truncated, original_length, provider, mode, latency_ms, attempts} — truncated: true means content was cut at WEB_RETRIEVAL_EXTRACT_CHAR_LIMIT and original_length is the pre-cut character count; failed URLs carry an error field instead. A CDN/CAPTCHA interstitial (Cloudflare "Just a moment…", Akamai "Access Denied") is not returned as content: it is a fallback-eligible error, so the chain tries the next provider. Private, loopback and link-local targets are fetched like any other URL by default; with WEB_RETRIEVAL_BLOCK_PRIVATE=1 they are refused instead. That opt-in check is a target heuristic, not SSRF protection (no protection against DNS rebinding or a redirect hop at the provider). Note: JS-rendered, login-walled or CAPTCHA-protected pages are not guaranteed. PRIVACY: each entry echoes the caller's URL verbatim in url, on success and on failure, so the link stays usable — a credential inside that URL (?token=, ?sig=, ?api_key=) is therefore returned in cleartext, not scrubbed (only an exact value of a provider key configured here is still stripped). error and attempts are scrubbed; url and content are not. The payload enters this conversation and may be recorded in session transcripts or chat logs and sent to the model provider serving it. Prefer short-lived signed URLs and revoke them after the fetch; redaction is not a confidentiality guarantee.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "web_fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
urlsNo
providersNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • addedInput schema / properties / providers
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Providers"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description carries the full burden and does so unusually well: it discloses the failover chain and its env override, automatic auth modes, truncation semantics tied to WEB_RETRIEVAL_EXTRACT_CHAR_LIMIT, CDN/CAPTCHA interstitials being treated as fallback-eligible errors, and that the private-IP check is a heuristic rather than SSRF protection (DNS rebinding, redirect hops). It also discloses the credential-leak risk in the returned `url` field, which fields are scrubbed versus not, and that payloads enter the conversation and transcripts.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and the param contract are front-loaded, and essentially every sentence adds a fact an agent could not get from the schema — truncation, interstitial handling, privacy leak. The tradeoff is a single unbroken paragraph in which the long privacy block is hard to scan, so structure is weaker than the content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though an output schema exists, the description usefully annotates the return payload's sharp edges — `truncated: true` versus `original_length`, and the `error` field on failed URLs. Combined with the failover, auth, and privacy coverage, nothing material is missing for an agent to call this correctly and safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does: `urls` is explained as a batch alternative with a max of 5, and `providers` is defined as a per-call chain reorder rather than a persistent setting. The one gap is the interaction between `url` and `urls` when both are supplied (schema defaults are empty string / null).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause gives a specific verb and resource — "Fetch one URL's page content as Markdown" — plus the defining mechanism ("automatic provider failover"). This is distinguishable from the web_search sibling, which is a query tool, without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the operational conditions clearly: a single `url` string or a `urls` array capped at 5 for batch, `providers` overriding the chain for this call, and the default vs. opt-in private-target behavior. It never names a sibling or an explicit when-not scenario, so routing to versus web_search is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools