Glean MCP Server
for AI Agents
Connect your AI agent to StackOne's Glean MCP server and give it 87 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
87 Agent Actions
Create, read, update, and delete across Glean — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Glean MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Agent Protection
Every Glean tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Glean call.
Tools Discovery →What is the Glean MCP Server?
A Glean MCP server lets AI agents read and write Glean data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Glean MCP server ships with 87 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Glean MCP Tools
Every action from Glean's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Agents
- List Agents
List the agents available in the Glean instance, optionally filtered by name.
- Get Agent
Retrieve the details of a single agent by ID.
Announcements
- Create Announcement
Create an announcement shown to a targeted set of users for a fixed period.
- Update Announcement
Update an existing announcement.
- Delete Announcement
Delete an announcement.
Answers
- Create Answer
Create a curated Answer holding a question and its answer.
- Get Answer
Read a single curated Answer.
- Update Answer
Update an existing curated Answer.
- Delete Answer
Delete a curated Answer.
Chats
- Get Chat
Retrieve a saved Chat and its full conversation history.
- List Chats
List the saved Chats belonging to the calling user.
- Delete Chats
Delete the given saved Chats and everything they contain.
- Chat
Hold a conversation with Glean AI and wait for the complete answer.
Chat Files
- Get Chat Files
Retrieve metadata for files a user uploaded for Chat.
- Delete Chat Files
Delete files a user uploaded for Chat.
Collections
- Create Collection
Create an empty Collection.
- List Collections
List every Collection visible to the caller.
- Get Collection
Retrieve a single Collection by ID.
- Update Collection
Update the properties of an existing Collection.
- Delete Collection
Delete one or more Collections by ID.
Collection Items
- Add Collection Items
Add items to a Collection.
- Update Collection Item
Update a single item inside a Collection.
- Delete Collection Item
Remove a single item from a Collection.
Datasource Instance Configurations
- Get Datasource Instance Configuration
Read the publicly exposed configuration values of a datasource instance.
- Update Datasource Instance Configuration
Update the publicly exposed configuration values of a datasource instance.
Data Loss Prevention Policys
- Create Data Loss Prevention Policy
Create a data loss prevention policy and start scanning against it.
- Get Data Loss Prevention Policy
Retrieve a single data loss prevention policy.
- Update Data Loss Prevention Policy
Update an existing data loss prevention policy.
Document Visibility Overrides
- Get Document Visibility Overrides
Check whether documents are hidden from Glean results.
- Set Document Visibility Overrides
Hide or unhide documents in Glean.
Findings Exports
- Create Findings Export
Start an export of data loss prevention findings.
- List Findings Exports
List the data loss prevention findings export jobs.
- Delete Findings Export
Delete a data loss prevention findings export.
Pins
- Create Pin
Pin a document as a result for a set of search queries.
- List Pins
List every pinned result in the instance.
- Get Pin
Retrieve a single pin by ID.
- Update Pin
Update the queries or audience of an existing pin.
- Delete Pin
Unpin a previously pinned result.
Shortcuts
- Create Shortcut
Create a go link pointing an alias at a destination URL.
- List Shortcuts
List the shortcuts the authenticated user owns or can edit.
- Get Shortcut
Retrieve a single shortcut by ID or by alias.
- Update Shortcut
Update an existing go link.
- Delete Shortcut
Delete a go link.
Skills
- Import Skills
Import one or more skills from resolved GitHub source URLs.
- List Skills
List the skills available to the authenticated user.
- Get Skill
Retrieve the metadata of a single skill by ID.
- Update Skill
Update the mutable metadata of a skill.
- Sync Skill
Refresh a GitHub-imported skill from its stored source URL.
- Delete Skill
Delete a skill and all of its versions.
Skill Versions
- List Skill Versions
List the versions of a skill.
- Get Skill Version
Retrieve the metadata of one version of a skill.
Other (36)
- Create Authentication Token
Create a Web SDK authentication token for the current user.
- Create One Time Report
Create a one-time data loss prevention report and run it immediately.
- Add Verification Reminder
Create a verification reminder for a document.
- Get Agent Schemas
Retrieve the input and output JSON schemas of an agent.
- Get Chat Application
Retrieve the details of a custom Chat application.
- Get Datasource Credential Status
Read the credential health of a datasource instance.
- Get Document Permissions
Read the emails of everyone with access to a document.
- Get Documents
Read documents and their metadata for a list of document IDs or URLs.
- List Documents By Facets
Read documents and their metadata matching a set of facet conditions.
- List Entities
List people, teams or custom entities matching the given filters and sort order.
- Get People
Read people details for the given person IDs or email addresses.
- List Data Loss Prevention Policies
List the data loss prevention policies configured on the instance.
- Get Report Status
Check whether a data loss prevention report has finished running.
- Get Insights
Retrieve the aggregate usage insights shown in the Glean Insights dashboards.
- List Messages
Retrieve messages from an indexed messaging datasource such as Slack or Microsoft Teams.
- Search
Retrieve results from the Glean index for a query and its filters.
- Get Feed
Retrieve the personalized Glean feed for the calling user.
- Get Recommendations
Retrieve documents recommended for a given URL or Glean document ID.
- List Tools
List the tools available to the caller, optionally filtered by tool name.
- Get Action Pack Auth Status
Check whether the caller is authenticated against the tool behind an action pack.
- Get Tool Server Auth Status
Check the caller's authentication status for a tool server.
- Get Tool Server Tools
Retrieve tool definitions by name from a tool server.
- List Verifications
List the verification state of the documents the calling user owns.
- Delete All Chats
Delete every saved Chat owned by the calling user.
- Report Activity
Report user activity on indexed documents such as views, edits and comments.
- Report Feedback
Report an interaction with a Glean result such as a click, view or manual rating.
- Run Agent
Run an agent and wait for the complete response.
- Check Datasource Authorization
List the datasource instances still awaiting per-user OAuth authorization.
- Rotate Datasource Credentials
Replace the credentials a datasource instance uses to reach its upstream system.
- Autocomplete
Retrieve query suggestions, operators and documents for a partially typed query.
- Preview Skill Source
Inspect a GitHub URL for skills without persisting anything.
- Summarize
Generate an AI summary of one or more indexed documents.
- Call Tool
Execute a tool with the supplied parameters.
- Authorize Action Pack
Start the third-party OAuth flow for an action pack.
- Authorize Tool Server
Start the third-party OAuth flow for a tool server.
- Verify Document
Set the verification state of a document.
Set Up Your Glean MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Glean in under 10 lines of code.
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More Documents & Knowledge MCP Servers
134+ actions
101+ actions
96+ actions
95+ actions
92+ actions
80+ actions
80+ actions
Glean Resources
The Best MCP Gateways for Glean in 2026
Best MCP gateways for Glean: keep Glean's native governance, add StackOne for Workday, SAP, UKG and ServiceNow actions. Composio and Zapier compared.
10 min
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Glean MCP Server FAQ
Does StackOne have a Glean MCP server?
Glean MCP server vs direct API integration — what's the difference?
How does Glean authentication work for AI agents?
origin_owner_id.Are Glean MCP tools vulnerable to prompt injection?
What is the context bloat of a Glean agent and how do I avoid it?
Can I limit which actions my Glean agent can access?
Can I create custom agent actions for my Glean MCP server?
When should I NOT use a Glean MCP server?
What AI frameworks and AI clients does the StackOne Glean MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.