Seed MCP Server
Enables creating and inspecting Seed tables and relationships through the Seed backend HTTP API.
README
Seed MCP Server
MCP server for creating and inspecting Seed tables and relationships through the existing seed-backend HTTP API.
Setup
npm install
npm run build
Configuration
Set either an access token:
SEED_API_BASE=http://localhost:3007
SEED_ACCESS_TOKEN=...
Or login credentials:
SEED_API_BASE=http://localhost:3007
SEED_ORG=visual-sql
SEED_EMAIL=admin@admin.com
SEED_PASSWORD=admin
For organization listing, set a Maint token or Maint password:
SEED_MAINT_ACCESS_TOKEN=...
# or
SEED_MAINT_PASSWORD=...
Run
npm start
Tools
seed_get_access_tokenseed_list_orgsseed_register_orgseed_create_orgseed_update_orgseed_delete_orgseed_list_tablesseed_get_tableseed_create_tableseed_add_relationshipseed_list_framesseed_get_frameseed_create_frameseed_update_frameseed_delete_framesseed_list_viewsseed_get_viewseed_create_viewseed_update_viewseed_delete_viewsseed_list_documentsseed_add_documentsseed_add_mock_dataseed_delete_documentsseed_grant_permission
seed_get_access_token
Get a Seed API access token for either a regular organization user or Maint. The MCP server prompts for credentials through the client instead of accepting them as tool arguments.
User token:
{ "type": "user" }
Maint token:
{ "type": "maint" }
seed_grant_permission
Grant a role access to a table/resource by creating a row in permissions and linking it to the role.
{
"resourceId": "accounts",
"access": 15,
"roleName": "admin"
}
Access bitmask: create 1, read 2, update 4, delete 8, full CRUD 15.
seed_create_frame
Create a frame on top of an existing table. Frames select the fields and relations that a view can render.
{
"name": "accounts_frame",
"table": "accounts",
"label": "Accounts",
"fields": [
{ "name": "name", "type": "string", "label": "Name" },
{ "name": "accountType", "type": "enum", "label": "Account Type" }
],
"relations": []
}
Optional filter/order inputs are JSON strings: fieldFiltersJson, fieldOrderJson, and relationFiltersJson.
For user-scoped frames, use relationFiltersJson with Seed's current-user sentinel. The backend treats
"___current___" as the logged-in user's email when the dot-walk path ends at a related users.email
field. The path uses Seed's generated join table name:
{
"relationFiltersJson": "{\"[Op.and]\":[{\"users_contacts_user.email\":{\"[Op.like]\":\"___current___\"}}]}"
}
Join table names are generated as <lexicographically larger table>_<lexicographically smaller table>_<relationName>.
For example, a contacts.user -> users relation uses users_contacts_user.email, while
voice_notes.user -> users uses voice_notes_users_user.email.
seed_create_view
Create a view on top of an existing frame.
{
"name": "accounts_web_view",
"frame": "accounts_frame",
"label": "Accounts",
"layoutJson": "{\"device\":\"web\",\"group\":\"CRM\",\"list\":{\"type\":\"default\"}}"
}
Optional role inputs are JSON strings: viewRolesJson and editRolesJson.
seed_list_documents
List documents from a table, usually to inspect data or find ids for relations.
{
"tableName": "accounts",
"pageNumber": 0,
"pageSize": 25
}
seed_add_documents
Add exact Seed document payloads. Use this when rows include relations.
{
"tableName": "contacts",
"documents": [
{
"fields": {
"firstName": "Avery",
"lastName": "Stone",
"email": "avery@example.com"
},
"relations": {
"account": {
"type": "OneToOne",
"table": "accounts",
"id": "1"
}
}
}
]
}
seed_add_mock_data
Add simple field-only mock rows. Use seed_add_documents when you need relations.
{
"tableName": "accounts",
"rows": [
{
"name": "Horizon Capital",
"accountType": "Company",
"vertical": "Dealmakers"
}
]
}
seed_delete_documents
Delete documents by id. Useful for cleaning up generated mock data.
{
"tableName": "accounts",
"documentIds": ["1", "2"]
}
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。