← elephant.md

INDIVIDUAL MCP TOOL

update_document

Update metadata or content of a document you own.

elephant.mdnone authenticationAvailability not checked

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 endpoint

elephant.md

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.elephant]
url = "https://elephant.md/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "elephant": {
      "type": "http",
      "url": "https://elephant.md/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: elephant
Remote MCP URL: https://elephant.md/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": {
    "elephant": {
      "url": "https://elephant.md/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "elephant": {
      "type": "http",
      "url": "https://elephant.md/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "elephant",
  "transport": "streamable-http",
  "url": "https://elephant.md/mcp"
}
MCP Inspector

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

Related tools

  • search — Search documents on elephant.md (full-text + semantic, fused).
  • fetch — Fetch a document's content by username and slug.
  • trending — Get trending documents on elephant.md
  • list_user_docs — List a user's public documents
  • discover — Discover documents using natural language semantic search (powered by embeddings).
  • get_context — Route-then-read in ONE call: searches your context for `query`, returns ranked summary cards, and inlines the top documents' full content up to `tokenBudget` so you get usable context in a single round trip.
  • find_collections — Find the most relevant COLLECTIONS for a query — route to the right collection, then `search_collection` or `fetch_collection` it.
  • search_collection — Search WITHIN one collection (full-text + semantic, scope-gated to that collection's members).