Low Risk

memory_read

Read a memory file by filename. Searches personal first, then shared.

How to control memory_read ↓

What memory_read does on Odoo Claude MCP

AI agents call memory_read to retrieve information from Odoo Claude MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why memory_read needs a policy

This tool retrieves data from memory files without creating, modifying, or deleting anything. The search-and-retrieve pattern is characteristic of Read operations. While the content of memory files could theoretically be sensitive, the tool itself performs only a non-destructive lookup operation. Severity is low because reading files has minimal blast radius compared to modification or execution risks.

From the tool's definition Tool name is "memory_read" and description states it "Read[s] a memory file by filename" with search behavior ("personal first, then shared"). The verb "read" and the query-like search mechanism indicate data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access memory_read gives an agent:

How to control memory_read

PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo Claude MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_read:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_read": {}
  }
}

memory_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Odoo Claude MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about memory_read

What does the memory_read tool do? +

Read a memory file by filename. Searches personal first, then shared. It is categorised as a Read tool in the Odoo Claude MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on memory_read? +

Register the Odoo Claude MCP server in PolicyLayer and add a rule for memory_read: 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 Odoo Claude MCP. Nothing to install.

What risk level is memory_read? +

memory_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit memory_read? +

Yes. Add a rate_limit block to the memory_read 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.

How do I block memory_read completely? +

Set action: deny in the PolicyLayer policy for memory_read. 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.

What MCP server provides memory_read? +

memory_read is provided by the Odoo Claude MCP server (rosenvladimirov/odoo-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Odoo Claude MCP tool call.

Start from Odoo Claude MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

180 Odoo Claude MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.