Chat with Glean Assistant using Glean's RAG Example request: { "message": "What are the company holidays this year?", "context": [ "Hello, I need some information about time off.", "I'm planning my vacation for next year." ] }
AI agents call chat to retrieve information from Local without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
context | array | — | Optional previous messages for context. Will be included in order before the current message. |
message | string | Yes | The user question or message to send to Glean Assistant. |
Parameters from the server's own tool schema.
This tool retrieves and queries information from Glean's knowledge base through conversational interface. It is a read-only operation that returns data without modifying, executing code, or causing side effects. The RAG pattern confirms it is a retrieval mechanism. Severity is low because misuse would only expose information the user might already have access to through normal Glean search operations.
From the tool's definition Tool description states 'Chat with Glean Assistant using Glean's RAG' (Retrieval-Augmented Generation). The example request demonstrates querying for information ('What are the company holidays this year?') with context messages.
Attacks that exploit this kind of access
Chat with Glean Assistant using Glean's RAG Example request: { "message": "What are the company holidays this year?", "context": [ "Hello, I need some information about time off.", "I'm planning my vacation for next year." ] }. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
chat accepts 2 parameters: context, message. Required: message. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for chat: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Local. Nothing to install.
chat is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the chat rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for chat. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
chat is provided by the Local MCP server (@gleanwork/local-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →