Nomic Atlas MCP by usefulapi

Working · 894 ms

io.usefulapi/nomic-atlasv1.21.0 Domain verified

Semantic nearest-neighbour search over your datasets, plus indices and projections.

Data & Databases

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://nomic-atlas.usefulapi.io/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

nomic_get_dataset Read-only

Fetch a dataset (Atlas calls it a project) by id — its schema, size, indices and projections. Atlas: GET /v1/project/{id}.

dataset_idstring, required

The dataset's id (a UUID).

Tools (9)

nomic_get_dataset

Fetch a dataset (Atlas calls it a project) by id — its schema, size, indices and projections. Atlas: GET /v1/project/{id}.

read-only

Argument	Type	Description
dataset_id*	string	The dataset's id (a UUID).

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "dataset_id"
  ],
  "properties": {
    "dataset_id": {
      "type": "string",
      "description": "The dataset's id (a UUID)."
    }
  }
}

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}.

read-only

Argument	Type	Description
dataset_slug*	string	The dataset's slug.
organization_slug*	string	The organisation's slug.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "organization_slug",
    "dataset_slug"
  ],
  "properties": {
    "dataset_slug": {
      "type": "string",
      "description": "The dataset's slug."
    },
    "organization_slug": {
      "type": "string",
      "description": "The organisation's slug."
    }
  }
}

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}.

read-only

Argument	Type	Description
job_id*	string	The index job's id.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job_id"
  ],
  "properties": {
    "job_id": {
      "type": "string",
      "description": "The index job's id."
    }
  }
}

nomic_get_organization

Fetch an organisation by slug, with the datasets it holds. Atlas: GET /v1/organization/{slug}.

read-only

Argument	Type	Description
slug*	string	The organisation's slug, from nomic_get_user.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "The organisation's slug, from nomic_get_user."
    }
  }
}

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.

read-only

Argument	Type	Description
projection_id*	string	The projection's id.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "projection_id"
  ],
  "properties": {
    "projection_id": {
      "type": "string",
      "description": "The projection's id."
    }
  }
}

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.

read-only

Argument	Type	Description
tag_id*	string	The tag's id, from nomic_list_tags.
dataset_id*	string	The dataset's id.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "dataset_id",
    "tag_id"
  ],
  "properties": {
    "tag_id": {
      "type": "string",
      "description": "The tag's id, from nomic_list_tags."
    },
    "dataset_id": {
      "type": "string",
      "description": "The dataset's id."
    }
  }
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}

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.

read-only

Argument	Type	Description
dataset_id*	string	The dataset's id.
projection_id*	string	The projection's id.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "dataset_id",
    "projection_id"
  ],
  "properties": {
    "dataset_id": {
      "type": "string",
      "description": "The dataset's id."
    },
    "projection_id": {
      "type": "string",
      "description": "The projection's id."
    }
  }
}

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.

read-only

Argument	Type	Description
k*	integer	How many neighbours to return per seed, 1-100.
datum_ids*	array	Ids of the seed records to find neighbours of.
atlas_index_id*	string	The index to search. Read it from the dataset returned by nomic_get_dataset.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "atlas_index_id",
    "datum_ids",
    "k"
  ],
  "properties": {
    "k": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "How many neighbours to return per seed, 1-100."
    },
    "datum_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Ids of the seed records to find neighbours of."
    },
    "atlas_index_id": {
      "type": "string",
      "description": "The index to search. Read it from the dataset returned by nomic_get_dataset."
    }
  }
}