Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BASE_URLYesPublic base URL, no trailing slash, e.g. https://outlook-mcp-proxy.your-tailnet.ts.net
LOG_LEVELNoOptional. Python logging level (INFO, WARNING, DEBUG, etc.). Defaults to INFO.INFO
JWT_SECRETYesSecret for signing session JWTs (any random string)
MS_CLIENT_IDYesAzure App registration Application (client) ID
MS_CLIENT_SECRETYesAzure App registration client secret — expires within 24 months, see Notes
ATTACHMENT_MAX_MBNoOptional. Max attachment size (1–25MB, decoded) get_attachment will fetch. Defaults to 3. Attachment bytes return as base64 text inside the MCP tool result — straight into the calling LLM's context, not just over the network.3
READ_ONLY_ALIASESNoOptional. Comma-separated list of connector aliases (e.g. family) that should be restricted to read-only access — no send, draft, folder/category changes, or move/trash.
API_RETRY_ATTEMPTSNoOptional. Total attempts (1–5) for a write-tool call before giving up. Defaults to 2. Honors a Retry-After response header from Graph when present.2
ALLOWED_REDIRECT_URISNoOptional. Comma-separated allowlist of OAuth redirect URIs /authorize will accept. Defaults to Claude.ai's callback (https://claude.ai/api/mcp/auth_callback) — only change this if you're connecting a non-Claude.ai MCP client.https://claude.ai/api/mcp/auth_callback

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