exa-search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| tools | No | Comma-separated list of tools to enable (e.g., web_search_exa,research_paper_search,company_research,crawling,competitor_finder,linkedin_search,wikipedia_search_exa,github_search) | |
| EXA_API_KEY | Yes | Your Exa API key from dashboard.exa.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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_search_exaA | Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites. |
| get_code_context_exaA | Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| web_search_help | Get help with web search using Exa |
| code_search_help | Get help finding code examples and documentation |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| tools_list | List of available Exa tools and their descriptions |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one is specialized for programming-related searches (code context), while the other is for general web searches. There is no overlap in functionality, and the descriptions explicitly differentiate their use cases.
Both tools follow a consistent naming pattern: they use snake_case and start with a verb (get, search) followed by a noun phrase (code_context, web). This makes them predictable and easy to understand.
With only two tools, the server feels under-scoped for a search domain. While the tools cover distinct areas (code and web), a search server typically benefits from more granular operations like filtering, pagination, or specialized search types, making this set feel thin.
The tools cover two key search domains (code and web), but there are notable gaps. For example, there are no tools for advanced search configurations, result management, or handling different content types beyond code and general web pages, which limits flexibility for agents.