Schema | MCP-Hound

MCP-Hound

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_PORT`	No	HTTP server port (HTTP mode only)	3000
`GITEA_URL`	No	Gitea server URL (for file context)
`HOUND_URL`	No	Hound server URL	http://localhost:6080
`GITHUB_URL`	No	GitHub URL (for Enterprise, otherwise defaults)	https://github.com
`GITEA_TOKEN`	No	Gitea API token (for private repos)
`GITHUB_TOKEN`	No	GitHub personal access token (for private repos)
`GITEA_TIMEOUT`	No	Gitea API timeout (ms)	10000
`HOUND_TIMEOUT`	No	Request timeout (ms)	30000
`GITHUB_TIMEOUT`	No	GitHub API timeout (ms)	10000
`HOUND_CONFIG_DIR`	No	Path to Hound config directory (for auto-indexing)
`CORS_ALLOWED_ORIGIN`	No	Allowed CORS origin (leave empty for permissive dev mode)
`HOUND_WEBHOOK_SECRET`	No	Secret for Gitea webhook signature verification

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`	{}

Functions exposed to the LLM to take actions

Name	Description
hound_searchA	Search code across all indexed repositories using regex patterns. Returns matching files and lines with deep links.
hound_reposA	List all repositories indexed by Hound code search. Returns repository names and URLs.
hound_file_contextB	Get extended context around a specific line in a file. Useful for understanding code around a search match.

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/jmagly/mcp-hound'

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