Modelglass MCP
Provides a Model Context Protocol pricing feed for agents, enabling access to sourced, time-versioned registry data for AI model pricing across image, language, video, and audio modalities. It supports both stdio and HTTP transports for integration.
Endpoint and access
API key: create a key with the vendor first; your client sends it as an authorization header on every request.
https://modelglass-api.vercel.app/mcpChecks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Retrieve AI model pricing data via MCP
- Compare AI model capabilities and costs
- Route agents to cheapest capable models
Source and maintenance
- Maintenance checked
Tools
Reported by the attributed source; not independently observed by Koskamo.
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-06: 1 of 1 checks answered
- 2026-11-07: 2 of 2 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 167 ms
- 95th percentile latency
- 167 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 167 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http modelglass-mcp https://modelglass-api.vercel.app/mcpCodex
codex mcp add modelglass-mcp --url https://modelglass-api.vercel.app/mcpCursor
{
"mcpServers": {
"modelglass-mcp": {
"url": "https://modelglass-api.vercel.app/mcp"
}
}
}Cline
{
"mcpServers": {
"modelglass-mcp": {
"type": "streamableHttp",
"url": "https://modelglass-api.vercel.app/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"modelglass-mcp": {
"type": "http",
"url": "https://modelglass-api.vercel.app/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http modelglass-mcp https://modelglass-api.vercel.app/mcpClaude Desktop
https://modelglass-api.vercel.app/mcpWindsurf
{
"mcpServers": {
"modelglass-mcp": {
"serverUrl": "https://modelglass-api.vercel.app/mcp"
}
}
}Let your agent find its tools
Find servers like Modelglass MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.