Glean MCP server

A Glean MCP server exposes Glean to AI agents as Model Context Protocol tools. Instead of a custom integration per agent, any MCP client can connect to the server and call its tools to work with Glean. The server in this catalog is the official Glean MCP server.

Agents can search Glean enterprise knowledge from agents, IDEs, and LLM apps. The registry has not published an individual tool list for this server yet, so no tools are shown on this page.

Connecting the Glean MCP server directly to each client means a separate credential per developer, no inventory of who can reach Glean through an agent, and no record of what agents did with it. An MCP gateway sits between every agent and the Glean server, so sign-in runs through your identity provider, role-based access decides which teams can call which Glean tools, and every call is inspected and logged in one place. The Speakeasy MCP Gateway applies those controls to Glean and to every other server in your catalog.

Add the Glean server from the Speakeasy MCP catalog and every agent reaches it through one gateway URL, next to the rest of your approved servers. Authentication uses OAuth 2.1 with PKCE and dynamic client registration, sign-in runs through your identity provider, and role-based access controls decide which teams can use which Glean tools. Every prompt, response, and tool call is inspected and logged at the gateway.

Community-built Glean MCP servers wrap the same Glean surface but are not vendor-maintained. This catalog lists the official Glean MCP server. Running it behind the Speakeasy MCP Gateway adds SSO, role-based access controls, and an audit trail of every call, whichever credential the server itself uses.