epovest-mcp
Make AIs recommend your business. Measures how AI assistants answer the questions your market asks, which sources they cite, and gives the levers to shape those answers. 43 tools on a hosted Streamable HTTP endpoint at https://mcp.epovest.com/mcp
README
Epovest MCP server
With Epovest, businesses make AIs recommend them.
This is the official MCP server for Epovest. It is hosted: there is nothing to install and no package to build. Point your MCP client at the endpoint below and your assistant gets the same 43 tools the app itself is built on.
https://mcp.epovest.com/mcp
- Transport: Streamable HTTP
- Authentication: OAuth 2.1 with PKCE, or an API key as a Bearer token
- Official registry:
com.epovest/ai-visibility - Agent documentation: epovest.com/docs/api.md
What your assistant can do
Epovest measures how AI assistants answer the questions your market asks, which sources they cite, and gives the levers that shape those answers. Every tool below acts on the account that owns the API key.
Canon, the reference text a brand keeps stable and versioned: list_projects, create_project,
update_project_canon.
Tracking, the measurement itself: list_trackers, create_tracker, update_tracker,
start_tracker, pause_tracker, get_results for the score series, get_responses for the raw
engine answers, plus list_keyword_discoveries, accept_keyword_discovery,
dismiss_keyword_discovery and restore_keyword_discovery for the questions the measurement
suggests next.
Surfaces, the pages a brand writes itself: list_surfaces, create_surface, update_surface,
tick_surface_checklist, mark_surface_aligned, delete_surface, restore_surface.
Atlas, the map of the sources AI assistants listen to: list_sources, get_source.
Corroborations, where a third party speaks about the brand: list_corroborations,
create_corroboration, update_corroboration, archive_corroboration, plus
list_corroboration_candidates and dismiss_corroboration_candidate, which derive candidates from
what the engines already returned.
Logbook, the dated record of what was done, read against the curves: get_logbook,
create_logbook_entry, update_logbook_entry, delete_logbook_entry.
Quests, the action queue: list_quests, create_quest, update_quest, complete_quest,
dismiss_quest.
Account: get_credits reads the prepaid balance, topup_credits returns a hosted payment link
for the user to open. Nothing is ever charged without them.
Support, served even when data access has lapsed: contact_support, list_support_threads,
get_support_thread. A human answers in the thread.
Design notes for agents
- Measurement runs on prepaid credits:
create_trackerprepares a tracker as a draft, andstart_trackerlaunches its measurement against the balance. Read the balance first withget_credits. - Removals are reversible, and the inverse gesture lives in the same surface: archive and unarchive a corroboration, delete and restore a surface. Each gesture states a state rather than toggling a switch, so a replay is safe in both directions.
- Errors come back as the JSON envelope of the REST API v1: same codes, same meaning, whatever the transport.
- Pricing lives on epovest.com/pricing.
Company
Epovest is a brand operated by Sels de Rehy, LLC, a limited liability company incorporated in the State of Delaware, United States, serving clients worldwide.
Terms and privacy: epovest.com/en/terms, epovest.com/en/privacy.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。