Skip to main content
Glama
DeepSeek Search Everywhere MCP

DeepSeek Search Everywhere MCP

deepseek_fetch_many

Read-onlyIdempotent

Fetch up to 10 known web pages in parallel as clean Markdown in one call, optionally extracting query-relevant snippets and returning partial results for failed URLs.

Instructions

Read up to 10 known web pages in parallel as clean Markdown in one call.

Use it when the URLs are known and you need their text or matching excerpts (query=); fetches up to 5 at a time. $0.00075 per URL; each page gets up to max_chars_per_url (default 4,000) and all pages together up to max_total_chars (default 20,000). Skips blanks, fetches duplicates once, keeps input order and reports a failed URL in place (partial: true). Content is sanitized.

When NOT to use: discovering pages (deepseek_search_many), one page with section or offset selectors (deepseek_fetch), fields as JSON (deepseek_extract_many), or a synthesized answer (deepseek_research).

Returns: {"ok": True, "results": [{"url": str, "ok": bool, "content": str, ...}], "partial": bool, "cost_usd": float}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "urls": "<urls>"
    },
    "name": "deepseek_fetch_many"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsYesList of HTTP/HTTPS URLs to fetch in parallel (max 10 URLs)
cleanNoRemove Markdown backslash escapes from the page text (default True)
queryNoOptional query to extract relevant snippets from each page (default None)
refreshNoBypass local cache and fetch fresh pages from upstream (default False)
deadlineNoOverall timeout deadline in seconds; partial results returned on expiry
max_total_charsNoMax total characters across all fetched URLs (default 20000)
max_chars_per_urlNoMax characters of page text returned per URL (default 4000)
strip_boilerplateNoRemove cookie banners and site UI boilerplate from content (default True)
fallback_to_searchNoOn 404, fall back to searching exact URL in index (default True)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv3.0.0
    • addedInput schema / properties / clean / description
      Added value: +"Remove Markdown backslash escapes from the page text (default True)"
    • addedInput schema / properties / deadline / description
      Added value: +"Overall timeout deadline in seconds; partial results returned on expiry"
    • addedInput schema / properties / fallback_to_search / description
      Added value: +"On 404, fall back to searching exact URL in index (default True)"
    • addedInput schema / properties / max_chars_per_url / description
      Added value: +"Max characters of page text returned per URL (default 4000)"
    • addedInput schema / properties / max_total_chars / description
      Added value: +"Max total characters across all fetched URLs (default 20000)"
    • addedInput schema / properties / query / description
      Added value: +"Optional query to extract relevant snippets from each page (default None)"
    • addedInput schema / properties / refresh / description
      Added value: +"Bypass local cache and fetch fresh pages from upstream (default False)"
    • addedInput schema / properties / strip_boilerplate / description
      Added value: +"Remove cookie banners and site UI boilerplate from content (default True)"
    • addedInput schema / properties / urls / description
      Added value: +"List of HTTP/HTTPS URLs to fetch in parallel (max 10 URLs)"
  2. Changed1 schema field changedv2.2.0
    • addedInput schema / properties / fallback_to_search
      Added value: +{
      +  "default": true,
      +  "title": "Fallback To Search",
      +  "type": "boolean"
      +}
  3. Changed2 schema fields changedv2.0.1
    • addedInput schema / properties / deadline
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Deadline"
      +}
    • addedInput schema / properties / query
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Query"
      +}
  4. Changed1 schema field changedv1.0.0
    • addedInput schema / properties / strip_boilerplate
      Added value: +{
      +  "default": true,
      +  "title": "Strip Boilerplate",
      +  "type": "boolean"
      +}
  5. First observedv0.2.0

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses concurrency (up to 5 at a time), per-URL pricing ($0.00075), blank skipping, duplicate collapsing, input-order preservation, and in-place failure reporting via partial:true. The main thing it doesn't cover is cache behavior and how refresh interacts with cost, which the schema only hints at.

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?

Dense but well ordered: capability, selection rule, cost/limits, then a NOT-to-use block. Every item is substantive, though the per-URL and total character defaults duplicate what the schema already states verbatim, so a small amount of text is not strictly earning its place.

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?

For a 9-parameter parallel-fetch tool with a full output schema, the description covers cost, limits, failure semantics, and sibling routing. The return-shape sentence is technically redundant with the output schema but harmless and confirms the partial-result contract.

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 coverage is 100%, so the baseline is 3; the description earns an extra point by explaining the interplay between the two budgets (each page capped by max_chars_per_url, all pages capped by max_total_chars) and by calling out query= as the excerpt mechanism. It still just restates the default values (4,000 / 20,000) rather than adding new semantic detail.

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?

Opens with a specific verb, resource, and hard scope limit: 'Read up to 10 known web pages in parallel as clean Markdown in one call.' The 'known' qualifier and the 10-URL ceiling make it immediately distinguishable from the search and single-fetch siblings.

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

Usage Guidelines5/5

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

Gives a positive selection rule ('when the URLs are known and you need their text or matching excerpts (query=)') and an explicit exclusion block routing to four named siblings by scenario: discovery, single-page with selectors, JSON fields, and synthesized answers. No inference required.

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