Schema | kagi-mcp-gpt-5.6-sol-ultra

kagi-mcp-gpt-5.6-sol-ultra

Describes the environment variables required to run the server.

Name	Required	Description	Default
`KAGI_TIMEOUT_MS`	No	Timeout in milliseconds for Kagi requests. Default: 15000, allowed 1000-30000.	15000
`KAGI_CACHE_TTL_MS`	No	Cache TTL in milliseconds. Default: 60000, allowed 0-600000.	60000
`KAGI_SESSION_TOKEN`	Yes	Your Kagi session token or complete Session Link from the Kagi Control Center. Required.
`KAGI_MAX_CONCURRENCY`	No	Maximum concurrent requests. Default: 2, allowed 1-4.	2

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
kagi_searchA	Search the signed-in user's Kagi account and return ranked organic results with Kagi-provided search snippets. The default returns one full 20-result lightweight page. Destination pages are not opened or fetched; paginate explicitly when more results are needed.
kagi_list_lensesA	List the signed-in account's active and inactive Kagi Lenses with stable numeric IDs. Use an active ID as kagi_search.lens; this reads settings and does not run a search.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/real-jiakai/kagi-mcp-gpt-5.6-sol-ultra'

If you have feedback or need assistance with the MCP directory API, please join our Discord server