Developer Tools
sosumi.ai
Provides tools to search and fetch Apple Developer documentation, including videos and external Swift-DocC docs, returning structured results as markdown.
ENDPOINT 1
https://sosumi.ai/mcp
MCP server metadata
- Name
- sosumi.ai
- Version
- 1.0.0
Known tools 4
searchAppleDocumentationSearch Apple Developer documentation and return structured results
Inferred read-onlyfetchAppleDocumentationFetch Apple Developer documentation and Human Interface Guidelines by path and return as markdown
Inferred read-onlyfetchExternalDocumentationFetch external Swift-DocC documentation by absolute https URL and return as markdown
Inferred read-onlyfetchAppleVideoTranscriptFetch transcript for an Apple Developer video path and return as markdown
Inferred read-onlyCONNECT 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.sosumi-ai]
url = "https://sosumi.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"sosumi-ai": {
"type": "http",
"url": "https://sosumi.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: sosumi-ai
Remote MCP URL: https://sosumi.ai/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": {
"sosumi-ai": {
"url": "https://sosumi.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"sosumi-ai": {
"type": "http",
"url": "https://sosumi.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "sosumi-ai",
"transport": "streamable-http",
"url": "https://sosumi.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.