Desearch MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DESEARCH_API_KEY | Yes | Your Desearch API key from console.desearch.ai/api-keys |
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
} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ai-searchC | AI search and analysis on web using Desearch AI |
| x-searchB | Search X (Twitter) using Desearch AI. Optional filters narrow by user, date, language, verification, media, and engagement. Sort stays Top. |
| web-searchB | SERP-style web search using Desearch. Returns ranked titles, links, and snippets. |
| web-links-searchB | Search the web for links using Desearch. Only the web source is accepted. |
| x-links-searchB | AI search for X (Twitter) post links using Desearch. Returns links from posts that match the prompt. |
| x-posts-by-urlsB | Fetch full X (Twitter) posts for a list of post URLs. |
| x-post-by-idB | Fetch a single X (Twitter) post by its ID. |
| x-posts-by-userB | Search X (Twitter) posts by a specific user, with an optional keyword query. |
| x-post-retweetersA | List users who retweeted an X (Twitter) post. Pass cursor to page through more users. |
| x-user-postsC | Retrieve a user's X (Twitter) timeline posts by username. Pass cursor to page through more posts. |
| x-user-repliesB | Fetch posts and replies by an X (Twitter) user, with an optional keyword query. |
| x-post-repliesB | Fetch replies to an X (Twitter) post, with an optional keyword query. |
| extractA | Extract a public URL and return its content as plain text or HTML using Desearch. Preferred over web-crawl for new integrations. |
| web-crawlA | Crawl a public URL and return its content as plain text or HTML on the legacy Desearch /web/crawl route. The SDK marks webCrawl deprecated in favor of extract; this tool stays for parity with that route. Prefer extract for new integrations. |
| x-trendsB | Retrieve trending topics on X (Twitter) for a location by its WOEID using Desearch. |
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 15 tools
Most tools target distinct resource+action pairs (e.g., x-post-by-id vs x-posts-by-urls), and descriptions clarify differences. However, x-posts-by-user and x-user-posts are easily confused, and x-search vs x-links-search require careful reading to distinguish. Overall mostly distinct but with minor overlap.
Kebab-case is used throughout with clear prefixes (x- for X/Twitter, web- for web, ai- for AI). Minor inconsistencies exist in singular/plural (x-post-by-id vs x-posts-by-urls) and phrasing (x-posts-by-user vs x-user-posts), but the pattern remains predictable and readable.
15 tools is well-scoped for a search/crawl API covering multiple sources and endpoints. Each tool maps to a specific Desearch capability, and the deprecated web-crawl is justified for route parity.
Covers web search, AI search, link search, content extraction/crawl, X post retrieval by ID/URLs/user, replies, retweeters, and trends. Minor gaps include no direct X user profile lookup or hashtag search, but core workflows are well-covered.