search-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DDGS_PROXY | No | Optional outbound proxy for ddgs (read by the library itself). | |
| SEARCH_TIMEOUT | No | Seconds ddgs waits on each batch of engines. Default: 10. | |
| SEARCH_ATTEMPTS | No | Backend calls per search before reporting an error; each attempt reshuffles the engines. Default: 2. | |
| SEARCH_MCP_TOKEN | No | Bearer token required on HTTP transport (the /healthz endpoint stays open). Optional for stdio. |
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 | Search the web for CURRENT information: news, current events, anything recent/latest/today/this week, weather, prices, time-sensitive facts. Do NOT use for general knowledge like recipes, definitions, or history — those have better tools. Returns snippets (title, url, snippet), not full pages. |
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 1 tool
With only one tool, there is no possibility of confusing it with another. Its purpose is clearly limited to current/timely web search, with explicit negative guidance for general knowledge.
A single tool named `web_search` is descriptive, readable, and uses consistent snake_case. There is no pattern to violate or mix.
One tool is thin even for a narrow search server, though it may be intentional. The surface feels minimal rather than clearly well-scoped across typical search needs.
The tool covers core web search with useful parameters like region and result count. Minor gaps remain, such as no page-content retrieval or specialized news/image search, but the stated snippet-only behavior is clear.