Bring Enterprise Search
to OpenAI Agents SDK
Learn how to connect Glean to OpenAI Agents SDK and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Glean MCP Server?
Connect your Glean workspace to any AI agent and unlock enterprise knowledge through natural conversation.
What you can do
- Universal Search — Search across all connected data sources (Confluence, Slack, Google Drive, Jira, and more) from a single query
- Datasource Filtering — Focus searches on a specific connected platform for targeted results
- People Search — Find employees by name, role, expertise, or department across your organization
- Document Management — Index new documents, bulk-index batches, retrieve document metadata, and remove outdated content
- Curated Collections — Browse and inspect curated content collections for onboarding, policies, and shared knowledge
- AI Chat — Ask questions to Glean's AI assistant, which generates answers grounded in your organization's knowledge base
- Autocomplete — Get intelligent search suggestions based on organizational knowledge as you type
How it works
1. Subscribe to this server
2. Enter your Glean API Token from the Admin Console
3. Start searching your enterprise knowledge from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Knowledge Workers — find answers across Confluence, Slack, Drive, and Jira without switching between tools
- IT Administrators — index custom documents and manage curated collections programmatically
- Engineering Teams — search codebases, wikis, and design docs through a single conversational interface
Built-in capabilities (12)
Autocomplete suggestions
Bulk index documents
AI chat
Verify connectivity
Delete a document
Get collection details
Get document details
Index a document
List collections
Search across all content
g., Confluence, Slack, Google Drive). Search in specific datasource
Search people
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 12 tools from Glean through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Glean, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Glean in OpenAI Agents SDK
Glean and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Glean to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Glean in OpenAI Agents SDK
The Glean MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Glean for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Glean MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search across multiple data sources like Confluence, Slack, and Google Drive simultaneously?
Yes! The search tool queries all connected data sources in a single request. If you want to narrow results to a specific platform, use search_by_datasource with the datasource name (e.g., 'Confluence', 'Slack', 'Google Drive'). Use autocomplete to get intelligent suggestions as you refine your query.
Can I ask the Glean AI assistant questions about my organization's knowledge?
Yes. The chat tool sends a natural language question to Glean's AI assistant, which generates an answer grounded in your organization's indexed knowledge — including documents, wikis, Slack conversations, and Jira tickets. This is ideal for getting synthesized answers rather than just search results.
Can I index custom documents into Glean programmatically?
Yes. Use index_document to add a single document with a JSON payload containing title, body, URL, and metadata. For large batches, use bulk_index_documents to index multiple documents in one request. Use delete_document to remove outdated content and get_document to verify indexing status.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.