Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEO4J_URINoNeo4j connection URI; enables `push_graph_to_neo4j` (requires `pip install "repo-graph-mcp[neo4j]"`)
GITHUB_TOKENNoEnables private repos and higher GitHub rate limits (`GH_TOKEN` also works); without it the server uses anonymous access and falls back to `git clone` when rate-limited
NEO4J_DATABASENoNeo4j database name
NEO4J_PASSWORDNoNeo4j password
NEO4J_USERNAMENoNeo4j username
REPO_GRAPH_CACHE_DIRNoWhere downloads are unpacked and graphs are cached (gzipped JSON per commit)system temp
REPO_GRAPH_MAX_FILESNoFiles graphed per repo (shallowest first)6000
REPO_GRAPH_AUTH_TOKENNoHTTP mode: require `Authorization: Bearer …` or `?key=…`
REPO_GRAPH_MAX_FILE_KBNoLarger files are skipped768
REPO_GRAPH_UI_MAX_NODESNoNodes sent to the view (most structural first)6000
REPO_GRAPH_ALLOWED_HOSTSNoHTTP mode: enable DNS-rebinding protection for these hostnames
REPO_GRAPH_MAX_DOWNLOAD_MBNoArchive size limit300
REPO_GRAPH_ALLOW_LOCAL_PATHSNoAllow graphing directories on the server1 (stdio), 0 (HTTP)
REPO_GRAPH_MAX_CONCURRENT_BUILDSNoParallel builds in hosted mode2

Instructions

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.

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