deepseek-web-search

Overview Schema Source Related Servers Discussions Admin

Fetch URL as Markdown

fetch

Read-only

Retrieves a web page through DeepSeek and returns its raw JSON response with title and Markdown content, untruncated, for AI clients needing direct page data.

Instructions

Fetch a URL through DeepSeek and return the raw JSON response exactly as received.

The response is a JSON object with title (string) and content (Markdown). The content is not truncated by this server. The URL must be an absolute HTTP/HTTPS URL of at most 8192 characters and must not contain credentials. Billing: 5 CNY per 1,000 successful fetches. Rate limit: 25 QPS.

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": {
      "url": "<url>"
    },
    "name": "fetch"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Absolute HTTP/HTTPS URL to fetch. Must not contain credentials.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A3.7/5.0

Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: it discloses that content is not truncated by the server, the return shape, billing at 5 CNY per 1,000 successful fetches, and a 25 QPS rate limit. Those cost/throughput facts are exactly the operational context annotations cannot carry.

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?

Four short sentences, each doing a job: what it does, what returns, validity constraints, cost/rate. Nothing is padded, though the URL constraints duplicate the schema rather than adding value.

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?

There is no output schema, and the description compensates by describing the returned object's fields and the no-truncation guarantee. Cost and rate limits round out everything an agent needs to call this predictably.

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

Parameters3/5

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

Schema coverage is 100% and the single `url` parameter is already fully documented in the schema (absolute HTTP/HTTPS, no credentials, maxLength 8192). The description restates the same constraints without adding format examples or edge-case handling, so this is textbook baseline territory.

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

Purpose4/5

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

States a specific verb and resource ('Fetch a URL through DeepSeek') and says what comes back (raw JSON with title and Markdown content). The one blemish is the title saying 'as Markdown' while the body says 'raw JSON', which could briefly confuse, though the body reconciles it. It does not contrast with the `search` sibling.

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

Usage Guidelines2/5

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

The description gives hard input constraints (absolute HTTP/HTTPS, no credentials, 8192 chars) but never says when to reach for this tool versus `search` or when not to use it. An agent is left to infer that this is for a known URL rather than discovery.

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

fetchA
searchA