MCP server
Nomic Atlas MCP by usefulapi
Semantic nearest-neighbour search over your datasets, plus indices and projections.
- Runs
- Remotely
- Version
- 1.40.0
- Listing updated
- 4 days ago
About Nomic Atlas MCP by usefulapi
Nomic Atlas MCP by usefulapi is an MCP server. It runs as a hosted remote server, so there is nothing to install locally.
Install
Run in a terminal
claude mcp add --transport http nomic-atlas https://nomic-atlas.usefulapi.io/mcpAdd to Settings → Connectors → Add custom connector
https://nomic-atlas.usefulapi.io/mcpInstall in CursorOpens Cursor, which asks you to confirm. Or add it by hand:
Add to ~/.cursor/mcp.json
{
"mcpServers": {
"nomic-atlas": {
"url": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:
Add to .vscode/mcp.json
{
"servers": {
"nomic-atlas": {
"type": "http",
"url": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"nomic-atlas": {
"serverUrl": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"nomic-atlas": {
"type": "http",
"url": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Tools this server provides (9)
Read directly from the server.
- nomic_get_user
- Fetch the account the API key belongs to, including the organisations it can access. Start here — the organisation slug feeds the other tools. Atlas: GET /v1/user.
- nomic_get_organization
- Fetch an organisation by slug, with the datasets it holds. Atlas: GET /v1/organization/{slug}.
- nomic_get_dataset
- Fetch a dataset (Atlas calls it a project) by id — its schema, size, indices and projections. Atlas: GET /v1/project/{id}.
- nomic_get_dataset_by_slug
- Fetch a dataset by organisation slug and dataset slug — the human-readable path, and usually easier than finding the UUID. Atlas: GET /v1/project/{organization_slug}/{project_slug}.
- nomic_nearest_neighbors_by_id
- Semantic search: given the ids of records already in a dataset, return their nearest neighbours in embedding space, with distances. This is what Atlas is for — finding what resembles what across unstructured data. Needs a BUILT index; if the map is still building the call fails with a 500, so check nomic_get_index_job. Atlas: POST /v1/project/data/get/nearest_neighbors/by_id.
- nomic_get_index_job
- Fetch the status of an index-building job. Atlas indexes take time to build, and a vector search against an unbuilt map fails — this is how you tell which it is. Atlas: GET /v1/project/index/job/{job_id}.
- nomic_get_projection_schema
- Fetch the field schema of one projection — the columns available on its records. Atlas: GET /v1/project/projection/{projection_id}/schema.
- nomic_list_tags
- List the tags defined on one projection — the labelled selections a person made on the map. Atlas: GET /v1/project/projection/tags/get/all.
- nomic_get_tag_status
- Check whether a tag has finished computing its membership. A tag that is still building returns partial results. Atlas: GET /v1/project/projection/tags/status.
Nomic Atlas MCP by usefulapi FAQ
How do I add Nomic Atlas MCP by usefulapi to Claude Code?
Run this command in your terminal: claude mcp add --transport http nomic-atlas https://nomic-atlas.usefulapi.io/mcp