Skip to main content
Glama
perfectra1n

kubesearch-mcp

by perfectra1n

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoAlternative for MCP_HTTP_PORT.3000
GITHUB_TOKENNoLifts the GitHub API rate limit (60→5000/hr) used to resolve the latest release. Recommended.
MCP_HTTP_HOSTNoHTTP bind host (HTTP transport).0.0.0.0
MCP_HTTP_PORTNoHTTP listen port (HTTP transport). Also accepts PORT.3000
MCP_TRANSPORTNoTransport mode: stdio or http. Defaults to 'stdio' outside Docker, 'http' inside Docker.stdio
MCP_AUTH_TOKENNoIf set, every HTTP request must send Authorization: Bearer <token>.
KUBESEARCH_CACHE_DIRNoWhere the SQLite databases are cached. In Docker default is /data.~/.cache/kubesearch-mcp
KUBESEARCH_CLONE_DIRNoWhere ephemeral clones live.<cacheDir>/clones
KUBESEARCH_CLONE_MAX_MBNoReject/clean a clone whose tree exceeds this size.200
KUBESEARCH_ENABLE_CLONENoEnable the repo_* clone/review tools. Set 'false' to hide them entirely.true
KUBESEARCH_REFRESH_HOURSNoHow often to check for a newer daily release. 0 disables refresh.24
KUBESEARCH_UPSTREAM_REPONoSource repo for the databases (override only for forks/testing).whazor/k8s-at-home-search
KUBESEARCH_CLONE_MAX_REPOSNoMax concurrent cached clones (LRU-evicted).5
KUBESEARCH_CLONE_TTL_MINUTESNoAuto-delete a clone after this much inactivity.30
KUBESEARCH_CLONE_ALLOWED_HOSTSNoComma-separated host allowlist. Empty = any public host.
KUBESEARCH_CLONE_ALLOW_PRIVATENoPermit cloning from private/loopback/link-local/metadata addresses (SSRF guard off).false
KUBESEARCH_CLONE_TIMEOUT_SECONDSNoHard timeout for the git clone subprocess.120
KUBESEARCH_CLONE_REFRESH_ON_CLONENoOn a repeat clone of the same repo, git fetch + reset to latest commit.true

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/perfectra1n/kubesearch-mcp'

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