DeepSeek Web MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_API_KEY | Yes | Your DeepSeek API key, used to authenticate requests to DeepSeek's official Search and Fetch APIs. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search the web with DeepSeek and return ranked results, source URLs, and summaries. Use for current information. No chat model is called. |
| fetchA | Retrieve one public web page through DeepSeek and return its title and Markdown content. Use to read a known URL. No chat model is called. |
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 2 tools
fetch and search target clearly distinct operations: retrieving a known URL versus discovering URLs via query. The descriptions reinforce the boundary ('read a known URL' vs 'current information'), leaving no realistic chance of misselection.
Both names are lowercase single verbs in a consistent style, so the set reads predictably. It's a minor deviation from the stronger verb_noun convention (fetch_page, search_web) that would encode the resource.
Two tools is on the thin side for a web-access server, though each earns its place. It sits at the borderline where a couple of adjacent capabilities (e.g. batch fetch) might be expected.
fetch plus search cover the core read-only web domain with no dead ends for the stated purpose. Minor gaps exist around bulk retrieval, pagination, or content-type controls, but agents can work around them.