AI agents call read_documents 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 |
|---|---|---|---|
documentSpecs | array | Yes | List of document specifications to retrieve |
Parameters from the server's own tool schema.
This tool retrieves or queries documents by identifier without any side effects. It performs a passive read operation on existing data, matching the 'Read' category definition. The low severity reflects that retrieval of documents alone poses minimal risk unless the documents themselves contain highly sensitive information, which is not indicated in the tool description.
From the tool's definition Tool name is 'read_documents' and description states 'Read documents from Glean by ID or URL' with no modification, deletion, or execution capabilities indicated.
Attacks that exploit this kind of access
Read documents from Glean by ID or URL Example request: "documentSpecs": [ { "id": "doc-123", }, { "url": "https://example.com/doc2" } ]. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
read_documents accepts 1 parameter: documentSpecs. Required: documentSpecs. 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 read_documents: 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.
read_documents 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 read_documents 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 read_documents. 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.
read_documents 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 →