MCP server · Seam AI

Seam AI

Seam AI runs a remote, anonymous Model Context Protocol server on its documentation host. It is a documentation-search server (the Mintlify docs MCP surface), not a server over the Seam product API: the tools search and read the public docs corpus and file feedback, and the server's own instructions tell a client not to claim access to private or authenticated content. The server was probed live — initialize and tools/list both returned 200 without credentials — and the verbatim tools/list response is saved to seam-ai-mcp-tools.json. A /.well-known/mcp.json descriptor on the same host names the underlying Mintlify origin (https://signal-97.main-kill-isr.mintlify.me/mcp) as an equivalent endpoint with authentication "none".

Open endpoint → Seam AI provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Seam AI Type: Hosted endpoint Transport: http Host: docs.getseam.ai

Endpoint

https://docs.getseam.ai/mcp

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "seam-ai": { "url": "https://docs.getseam.ai/mcp" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "seam-ai": { "command": "npx", "args": ["-y", "mcp-remote", "https://docs.getseam.ai/mcp"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://docs.getseam.ai/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

search_seam_ai — Search across the Seam AI knowledge base to find relevant information, code examples, API references, and guidance.
query_docs_filesystem_seam_ai — Run a read-only shell-like query against a virtualized, in-memory filesystem containing the documentation corpus.
submit_feedback — Report a problem with this documentation site so the docs team can fix it.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.