ENDPOINT 1
https://docs.ojin.ai/~gitbook/mcp
MCP server metadata
- Name
- mcp-typescript server on vercel
- Version
- 0.1.0
Known tools 4
searchDocumentationSearch across the documentation to find relevant information, code examples, API references, and guides.
Inferred read-onlygetPageFetch the full markdown content of a specific documentation page from Ojin Documentation.
Inferred read-onlyaskQuestionAsk a natural-language question about Ojin Documentation and get a synthesized answer, with links to the source pages.
Inferred read-onlysendFeedbackReport an issue in the documentation of Ojin Documentation so the team can fix it.
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.mcp-typescript-server-on-vercel]
url = "https://docs.ojin.ai/~gitbook/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"mcp-typescript-server-on-vercel": {
"type": "http",
"url": "https://docs.ojin.ai/~gitbook/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: mcp-typescript-server-on-vercel
Remote MCP URL: https://docs.ojin.ai/~gitbook/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": {
"mcp-typescript-server-on-vercel": {
"url": "https://docs.ojin.ai/~gitbook/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"mcp-typescript-server-on-vercel": {
"type": "http",
"url": "https://docs.ojin.ai/~gitbook/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "mcp-typescript-server-on-vercel",
"transport": "streamable-http",
"url": "https://docs.ojin.ai/~gitbook/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.