Schema | gitlab-agent-mcp

gitlab-agent-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PORT`	No	MCP server listening port.	8000
`MAX_FILES`	No	Maximum number of files selected for analysis.	5
`GITLAB_URL`	Yes	GitLab server URL.
`GITLAB_TOKEN`	Yes	Personal Access Token used to access repositories and source code.
`ANALYSIS_MODEL`	No	Model used by the Repository Analysis Agent.	gpt-4
`MAX_FILE_CHARS`	No	Maximum number of characters loaded from each file.	15000
`OPENAI_API_KEY`	Yes	API key used to authenticate requests.
`DISCOVERY_MODEL`	No	Model used by the Repository Discovery Agent.	gpt-4
`OPENAI_BASE_URL`	Yes	Base URL of an OpenAI-compatible API endpoint.
`RELEVANCE_MODEL`	No	Model used by the Code Relevance Agent.	gpt-4
`MAX_SEARCH_RESULTS`	No	Maximum number of GitLab search results retrieved before reranking.	20
`OPENAI_USE_TRANSPORT`	No	Enables custom transport for providers that require non-standard authentication headers.	false

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

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/telkomdev/gitlab-agent-mcp'

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