mcp-exa
MCP Exa
一个公开 Exa 搜索功能的 Python MCP 服务器(无需 API 密钥)
mcp-name: io.github.daedalus/mcp-exa
安装
pip install mcp-exaRelated MCP server: Swift Poe Search MCP
使用方法
无需 API 密钥。该服务器使用 Exa 的公共 MCP 端点。
运行 MCP 服务器:
mcp-exa或作为模块使用:
python -m mcp_exa配置
可用工具
该服务器公开了以下 MCP 工具:
工具 | 描述 |
| 搜索任何主题的网络内容 |
| 从 GitHub、Stack Overflow 查找代码示例 |
| 获取特定 URL 的完整内容 |
| 带有过滤条件的高级搜索 |
MCP 客户端配置
Claude Desktop
添加到您的配置文件中:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"exa": {
"command": "mcp-exa"
}
}
}OpenCode
添加到您的 opencode.json 中:
{
"mcp": {
"exa": {
"type": "stdio",
"command": "mcp-exa",
"enabled": true
}
}
}开发
git clone https://github.com/daedalus/mcp-exa.git
cd mcp-exa
pip install -e ".[test]"
# run tests
pytest
# format
ruff format src/ tests/
# lint
ruff check src/ tests/
# type check
mypy src/Available Tools
9 toolsanswerB
Generate an answer to a query using Exa's search and LLM capabilities.
Inputs: query (required), text, system_prompt, model, +2 more. Returns: object
find_similarC
Find pages similar to a given URL using Exa.
Inputs: url (required), num_results, contents, include_domains, +10 more. Returns: object
get_contentsB
Retrieve contents for a list of URLs using Exa.
Inputs: urls (required). Returns: object
research_createB
Create a new research request using Exa.
Inputs: instructions (required), model, output_schema. Returns: object
research_getB
Get a research request by ID using Exa.
Inputs: research_id (required), events, output_schema. Returns: object
research_listC
List research requests using Exa.
Inputs: cursor, limit. Returns: object
research_poll_until_finishedA
Poll until research is finished using Exa.
Inputs: research_id (required), poll_interval, timeout_ms, events, +1 more. Returns: object
searchC
Perform a web search using Exa.
Inputs: query (required), num_results, contents, include_domains, +14 more. Returns: object
stream_answerC
Generate a streaming answer response using Exa.
Inputs: query (required), text, system_prompt, model, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Most tools have clear boundaries (search, get_contents, find_similar, research_*), but answer and stream_answer are nearly identical except for streaming behavior, which could cause misselection. find_similar and search are related but distinct enough with descriptions.
The research_* tools follow a consistent prefix pattern, but the rest mix bare verbs (search, answer), verb_noun (find_similar, get_contents, stream_answer), and a long descriptive phrase (research_poll_until_finished), creating an inconsistent feel.
9 tools is a reasonable size for a search and research server, covering immediate searches, content retrieval, and async research workflows. Slightly more than strictly necessary due to answer/stream_answer duplication, but not excessive.
The core search, similar, content, answer, and research lifecycle (create, get, poll, list) are covered. A notable gap is the lack of a cancel/delete research operation, but most main workflows are complete.
Maintenance
Related MCP Connectors
Official Exa MCP for web search, content fetching, and multi-step research.
Web search API and MCP server for developers building AI agents.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Unofficial Serper MCP — wraps the Serper Google Search API (serper.dev)
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that integrates real-time web search capabilities into AI assistants using the Exa API, providing both basic and advanced search functionality with formatted markdown results.144MIT
- AlicenseNot gradedqualityFmaintenanceAn MCP server that integrates with Poe's API to provide AI-powered search and research tools from Perplexity, Reka, Exa, and Linkup.28 npm8MIT
- AlicenseAqualityCmaintenanceAn MCP server that exposes Gemini's Deep Research Agent for comprehensive web research.2122 npm67 PyPI4MIT
- AlicenseAqualityBmaintenanceAn open-source MCP server providing AI agents with neural web search via Exa and tiered web fetch (Exa, local browser, Firecrawl) as a drop-in replacement for built-in web tools, preserving provenance and guarding against SSRF.69MIT