Glean Developer Platform
MCP Remote Server: Now Generally Available
Connect Claude Desktop, Cursor, Windsurf, and 20+ AI tools to your secure enterprise data in 5 minutes. One server URL unlocks your entire knowledge base — no code required.
- One connection, universal access – Works with Claude Desktop, Cursor, VS Code, Windsurf, ChatGPT, and more
- Enterprise-grade security – Respects your company's access controls automatically
- 5-minute setup – Just add server URL to any MCP client


Search and Chat with Your Data
Connect your company data and ship AI-powered chat in minutes. Glean's APIs are permission-aware from day one and scale with your security requirements.
- Instant answers from everywhere – Query docs, messages, tickets, and wikis in one API call
- Your permissions, preserved – Automatic access control based on user identity
- Deploy anywhere – Power chatbots, search bars, or AI assistants in any app
import os
from glean import Glean, models
with Glean(
instance='acme',
api_token=os.getenv('GLEAN_API_TOKEN', ''),
) as g:
res = g.client.chat.create(
messages=[
{
'fragments': [
models.ChatMessageFragment(
text='What are the company holidays this year?',
)
],
}
]
)
Run AI Agents
Run intelligent agents that orchestrate workflows, reason over your enterprise knowledge, and automate complex tasks across your organization.
- Multi-step reasoning – Agents that plan, execute, and iterate on complex workflows
- Enterprise knowledge at their fingertips – Full access to your organization's data and context
- Automate anything – From sales reports to IT tickets to HR processes
import os
from glean import Glean, models
with Glean(
instance='acme',
api_token=os.getenv('GLEAN_API_TOKEN', ''),
) as g:
agent_run = g.client.agents.create_and_stream_run(
agent_id='sales-assistant',
messages=[
{
'fragments': [
models.ChatMessageFragment(
text='Generate a sales report for Q4 2024',
)
],
}
]
)
Connect Any Data Source
Bring any data source into Glean with our powerful indexing APIs. Bulk upload documents, sync in real-time, and define custom properties.
- Bulk or streaming, your choice – Upload millions of documents or sync in real-time
- Your schema, your way – Define custom properties, relationships, and metadata
- Battle-tested at scale – Powers search across 100+ data sources for Fortune 500 companies
import os
from glean import Glean, models
with Glean(
instance='acme',
api_token=os.getenv('GLEAN_INDEXING_TOKEN', ''),
) as g:
document = models.DocumentDefinition(
id='doc-123',
title='Q4 Sales Report',
body='Our Q4 performance exceeded expectations...',
datasource='internal-docs'
)
g.indexing.index_document(document=document)