Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Semantic nearest-neighbour search over your datasets, plus indices and projections.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://nomic-atlas.usefulapi.io/mcpRun this in your terminal
claude mcp add --transport http nomic-atlas https://nomic-atlas.usefulapi.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"nomic-atlas": {
"url": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"nomic-atlas": {
"type": "http",
"url": "https://nomic-atlas.usefulapi.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://nomic-atlas.usefulapi.io/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
nomic_get_userFetch 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_organizationFetch an organisation by slug, with the datasets it holds. Atlas: GET /v1/organization/{slug}.
nomic_get_datasetFetch a dataset (Atlas calls it a project) by id — its schema, size, indices and projections. Atlas: GET /v1/project/{id}.
nomic_get_dataset_by_slugFetch 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_idSemantic 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 w
nomic_get_index_jobFetch 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_schemaFetch the field schema of one projection — the columns available on its records. Atlas: GET /v1/project/projection/{projection_id}/schema.
nomic_list_tagsList 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_statusCheck whether a tag has finished computing its membership. A tag that is still building returns partial results. Atlas: GET /v1/project/projection/tags/status.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain usefulapi.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 10 ms (HTTP 200)
No sign-in needed
Read 9 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.36.2) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Semantic nearest-neighbour search over your datasets, plus indices and projections. Hosted, no local install.
Live endpoint: https://nomic-atlas.usefulapi.io/mcp · Homepage: https://usefulapi.io
https://nomic-atlas.usefulapi.io/mcp.claude mcp add --transport http nomic-atlas https://nomic-atlas.usefulapi.io/mcp, then run /mcp to log in.{
"mcpServers": { "nomic-atlas": { "url": "https://nomic-atlas.usefulapi.io/mcp" } } }
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Nomic Atlas credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/nomic-atlas/
On first connect you'll paste your Nomic Atlas credentials. They are validated, stored per-user, and scoped to you — no keys in config files.
| Tool | Type | What it does |
|---|---|---|
nomic_get_user | read | Get the current user |
nomic_get_organization | read | Get an organisation |
nomic_get_dataset | read | Get a dataset by id |
nomic_get_dataset_by_slug | read | Get a dataset by name |
nomic_nearest_neighbors_by_id | read | Find similar records |
nomic_get_index_job | read | Get an index job |
nomic_get_projection_schema | read | Get a projection's schema |
nomic_list_tags | read | List a projection's tags |
nomic_get_tag_status | read | Get a tag's status |
nomic_atlas_usage_status | meta | Usage status (free-tier meter) |
nomic_atlas_request_feature | meta | Request a missing feature |
nomic_atlas_upgrade | meta | Upgrade to Pro or Pro+ |
nomic_atlas_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo or $90/yr (2 months free) | Unlimited* |
\*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to support@usefulapi.io.
Pro covers this server only. Subscribe with nomic_atlas_upgrade (it returns a Stripe Checkout link). Cancel any time with nomic_atlas_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running nomic_atlas_upgrade before then undoes the cancel. Or write to support@usefulapi.io.
MIT