INDIVIDUAL MCP TOOL

get_posts

You already have post at:// URIs — from get_backlinks, sample_jetstream, list_records, anywhere — and want them as readable posts with text, author, and engagement counts, up to 25 in one call.

aturi.tonone authenticationAvailability not checked

LIVE ENDPOINT

https://aturi.to/api/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_posts and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Potential side effects detected · medium confidence · heuristic, not a guarantee.

A tool name or description contains a write-action term.

Parent server

aturi.to

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.atmosphere]
url = "https://aturi.to/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "atmosphere": {
      "type": "http",
      "url": "https://aturi.to/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: atmosphere
Remote MCP URL: https://aturi.to/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "atmosphere": {
      "url": "https://aturi.to/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "atmosphere": {
      "type": "http",
      "url": "https://aturi.to/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "atmosphere",
  "transport": "streamable-http",
  "url": "https://aturi.to/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

resolve_link — You have a web URL (bsky.app, a Leaflet page, a Tangled repo, any Atmosphere client — or an arbitrary page that might declare AT Tags) or an at:// URI, and you want the record behind it plus every client that can open it, each with a ready URL.
list_waypoints — You want to know which Atmosphere clients exist and what each can do, with no record in hand: 25+ apps with the record types they render and whether they accept compose-intent links.
resolve_identity — You have an atproto handle, DID, or at:// URI and need the canonical identity behind it: the DID, the current handle, the PDS host where the repo lives, and the DID document summary (alsoKnownAs, declared services).
resolve_identities — You have 1 to 100 did:plc or did:web identifiers and need their current handles, PDS hosts, and PLC creation times in one call.
get_identity_history — You have an account and want its identity timeline: when it was created, every handle it has used, PDS migrations, and key rotations, from the PLC directory audit log.
describe_repo — You have an account and want the shape of its repository: which collections (lexicons) it actually holds, its PDS, when it last wrote, and its Bluesky-layer profile if one exists.
list_records — You know which repo and which collection (from describe_repo) and want the records themselves: one page of full record values with their at:// URIs, plus a cursor for the next page.
get_record — You have a record address — an at:// URI, or repo + collection + rkey — and want the record JSON.