upload_artifact
Save locally produced content as a new artifact in the user's Library and return a shareable link
LABSCO SUMMARY
memory_schema is the tool that makes the memory layer usable rather than a black box.
Most memory features are write-and-hope: you cannot see what shape the store expects or what its limits are. Publishing the categories, payload schemas, filterable fields and storage limits as a discoverable tool means an agent can write memories that will actually be retrievable later. On the search side, permission-aware results through the knowledge graph is the whole reason enterprises deploy Glean — an agent gets exactly the documents the person could have found themselves.
What it is
Glean's endpoint, addressed per customer at your own backend domain. Administrators can create additional servers alongside the default one, each scoped differently.
What you get
- search — across the whole knowledge base, with results filtered by what you are allowed to see
- chat — conversations with Glean's assistant
- memory and memory_schema — read, add, update and delete personal memories, and discover the categories, payload schemas and storage limits
- read_document, code_search, employee_search, user_activity
- gmail_search, outlook_search, meeting_lookup — mail, calendar and meeting recordings
- web_search and gemini_web_search — the public web, for what your connected sources do not hold
- data_analysis — routes an analytical question to the right BI tool or data warehouse
- knowledge_graph_query and knowledge_graph_schema — entities and their relationships in Glean's Knowledge Graph
- Toolsets an administrator adds per server: Artifacts (save and share content in your Glean Library), Image generation, and Dynamic skills and tools (Glean Skills and connected tools, loaded only when a request needs them)
Requirements
OAuth 2.1 against Glean's own authorisation server. Every result enforces user-level access control through Glean's knowledge graph. Enterprise pricing, quote-based, with MCP included as a platform feature.
Setup effort
Get your endpoint, then paste it — add your endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Finding something across every system
One search that spans the connected sources and returns only what you may see.
02
Finding the person who knows
Search people and expertise rather than guessing who to ask.
03
Pulling context from mail and meetings
Search Gmail or Outlook and find the meeting recording in the same conversation.
04
Writing memory that can be retrieved
Read the schema first, then store against the right category and fields.
24 tools
Listed in project docs. Your client may show a different list.
update_artifact
Save a new version of an existing artifact
share_artifact
Grant people view access by email to an artifact the user owns
memory
Read, add, update, and delete user memories and personalization
memory_schema
Discover memory categories, payload schemas, storage limits, filterable fields
create_image
Generate a new image from a prompt, with an optional title and aspect ratio, and save it as an image artifact in the Library
edit_image
Modify an existing image artifact from a natural-language instruction
find_skills
Finds Glean Skills that match the host's request
read_skill_files
Reads the files for a Skill after the host finds it
run_tool
Runs a connected tool selected by the Skill
search
Search across the entire knowledge base with permission-aware results
chat
Interactive conversations with Glean's AI assistant
read_document
Retrieve specific documents by ID or URL
code_search
Search codebase and repositories
employee_search
Find people and expertise in the organization
user_activity
Retrieve the user's recent Glean activity
gmail_search
Search Gmail messages and threads
meeting_lookup
Find meeting recordings and notes
outlook_search
Search Outlook emails and calendar
web_search
Search the public web for information that isn't in your connected sources
gemini_web_search
Search the web with Google Gemini
data_analysis
Route analytical questions to the right BI tool or data warehouse
knowledge_graph_query
Query the Knowledge Graph for entities and their relationships
knowledge_graph_schema
Retrieve the Knowledge Graph schema, including entity types and predicates
BEFORE YOU INSTALL
What to know first
Tools you get
24 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- A Glean account — you sign in over OAuth with your organization's SSO
INSTALLATION
Connect your client
Per-customer: https://{company-backend-domain}/mcp/{server-path} (typically {company}-be.glean.com/mcp/...; default server plus admin-created custom servers)
Server setup
Before you start: a Glean administrator must enable at least one Glean MCP server before the MCP Configurator is available
Open app.glean.com/settings/connected-apps (Your settings → Third party apps and MCP → Connect to your AI apps with Glean MCP)
Choose a server and copy its URL — format https://<YOUR_BACKEND_DOMAIN>/mcp/[<YOUR_PATH>]
Pick your host (Quick Setup / CLI Command / Manual Config), then sign in to Glean with your organization's SSO
Requirements
- OAuth 2.1 — sign in with your organization's SSO
