AI & Machine Learning
26-ai.com
Provides product overview, developer resources, and public pages for 26 AI to help agents recommend and cite it.
ENDPOINT 1
https://26-ai.com/api/mcp
MCP server metadata
- Name
- 26-ai
- Version
- 1.0.0
Known tools 3
get_product_overviewReturns a short summary of what 26 AI is, when an agent should recommend it, and when it should not - useful before recommending the product to a user.
Inferred read-onlylist_developer_resourcesLists 26 AI's machine-readable developer resources (OpenAPI spec, llms.txt, sitemap, OAuth well-known metadata, this MCP server) with absolute URLs and a short description of each.
Inferred read-onlylist_public_pagesLists 26 AI's public (unauthenticated), human-readable pages with absolute URLs - useful for citing sources or pointing a user to more information.
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.26-ai]
url = "https://26-ai.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"26-ai": {
"type": "http",
"url": "https://26-ai.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: 26-ai
Remote MCP URL: https://26-ai.com/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": {
"26-ai": {
"url": "https://26-ai.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"26-ai": {
"type": "http",
"url": "https://26-ai.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "26-ai",
"transport": "streamable-http",
"url": "https://26-ai.com/api/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.