Seed MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Seed MCP Server show me the accounts table"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 buildRelated MCP server: Attio MCP Server
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=adminFor organization listing, set a Maint token or Maint password:
SEED_MAINT_ACCESS_TOKEN=...
# or
SEED_MAINT_PASSWORD=...Run
npm startTools
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"]
}Available Tools
25 toolsseed_add_documentsA
Add exact Seed document payloads to a table. Use this when rows include relations.
Inputs: documents (required), tableName (required).
seed_add_mock_dataA
Add simple mock rows to a Seed table. Each row is treated as field values only; use seed_add_documents for relations.
Inputs: rows (required), tableName (required).
seed_add_relationshipB
Add or replace a relationship on an existing Seed table.
Inputs: relationName (required), relationType (required), sourceTableName (required), targetTableName (required), +1 more.
seed_create_frameA
Create a Seed frame on an existing table. Frames select table fields/relations and optional filters before creating views.
Inputs: name (required), table (required), fields (required), label, +5 more.
seed_create_orgA
Create a Seed organization with optional organization metadata. Requires the configured Seed user to have create access.
Inputs: name (required), email, other, phone, +11 more.
seed_create_tableB
Create a Seed table with fields and optional relationships.
Inputs: name (required), fields (required), label, relations, +1 more.
seed_create_viewB
Create a Seed view on an existing frame.
Inputs: name (required), frame (required), layoutJson (required), label, +3 more.
seed_delete_documentsA
Delete documents from a Seed table by id. Useful for cleaning up mock data.
Inputs: tableName (required), documentIds (required).
seed_delete_framesA
Delete Seed frames by name.
Inputs: frameNames (required).
seed_delete_orgA
Delete a Seed organization by name, including its organization database file when present. Requires delete access.
Inputs: name (required).
seed_delete_viewsB
Delete Seed views by name.
Inputs: viewNames (required).
seed_get_access_tokenA
Get a Seed API access token by prompting for credentials through the MCP client.
Inputs: type.
seed_get_frameB
Get Seed metadata for one frame.
Inputs: frameName (required).
seed_get_tableC
Get Seed metadata for one table.
Inputs: tableName (required).
seed_get_viewA
Get Seed metadata for one view.
Inputs: viewName (required).
seed_grant_permissionA
Grant a role access to a Seed resource by creating a permissions row and linking it to the role. Access bitmask: create=1, read=2, update=4, delete=8, full CRUD=15.
Inputs: resourceId (required), name, access, roleName.
seed_list_documentsA
List documents from a Seed table. Useful for finding record ids before creating related data.
Inputs: tableName (required), pageSize, orderJson, pageNumber, +1 more.
seed_list_framesC
List Seed frame metadata from the configured organization.
Inputs: pageSize, pageNumber, filtersJson.
seed_list_orgsB
List registered Seed organizations. Requires SEED_MAINT_ACCESS_TOKEN or SEED_MAINT_PASSWORD.
Inputs: pageSize, pageNumber, filtersJson.
seed_list_tablesA
List Seed table metadata from the configured organization.
Inputs: pageSize, pageNumber.
seed_list_viewsB
List Seed view metadata from the configured organization.
Inputs: pageSize, pageNumber, filtersJson.
seed_register_orgB
Register a new Seed organization with backend defaults. This calls the public organization register endpoint.
Inputs: orgName (required).
seed_update_frameB
Update Seed frame metadata by frame name.
Inputs: name (required), table (required), fields (required), label, +5 more.
seed_update_orgC
Update Seed organization metadata by organization name. Requires the configured Seed user to have update access.
Inputs: name (required), email, other, phone, +11 more.
seed_update_viewB
Update Seed view metadata by view name.
Inputs: name (required), frame (required), layoutJson (required), label, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Most tools are clearly distinct by resource and action, but there is some overlap between seed_register_org and seed_create_org, as well as between seed_add_documents and seed_add_mock_data. The descriptions help differentiate them, but an agent could still confuse the subtly different purposes.
All tools follow a consistent seed_<verb>_<noun> snake_case pattern. The verbs are predictable (list, get, create, update, delete, add) and the nouns correspond to resources. Minor pluralization differences (e.g., delete_frames vs delete_org) do not break the overall pattern.
With 25 tools, the server is at the upper boundary of the typical range, but the count is justified by covering multiple resources (orgs, tables, frames, views, documents, permissions). A few tools could be consolidated without loss of clarity, but the scope is still reasonable.
The tool surface has notable gaps: tables lack update and delete operations, documents lack update and get-by-id, and permissions only support grant without revoke. While the core workflows for frames and views are fully covered, these missing operations will require workarounds and may cause agent failures in common scenarios.
Maintenance
Related MCP Connectors
Read, create, update and delete records; inspect objects, fields and schema in your Knack database.
Query your Google Sheets as structured JSON: list sheets and tabs, read schemas, filter rows.
Shared, versioned tables with units, links and SQL. Agents read what your data means.
Read and write Rowflare bases (open-source Airtable alternative): records, tables, fields, totals.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables interaction with the AppFlowy Cloud API to manage workspaces, databases, and row operations. It provides tools for authentication, resource discovery, and full row manipulation including creation and upserts.94-
- FlicenseNot gradedqualityDmaintenanceProvides tools to interact with the Attio API, enabling management of resources in an Attio workspace.5-
- FlicenseNot gradedqualityDmaintenanceEnables reading and writing to Tableau Server or Tableau Cloud via the REST API, supporting operations on sites, projects, workbooks, views, and data sources.4-
- FlicenseAqualityDmaintenanceEnables LLMs to inspect database schemas and seed relational databases with custom data while automatically resolving foreign key relationships.4-