Generic Frappe list. doctype=DocType name; filters_json is a JSON list of [field, op, value] triples; fields_json is a JSON list of field names. Use this when the FranOS-specific tools don't fit (e.g. for ERPNext's Sales Invoice, GL Entry, Customer).
AI agents call frappe_list_docs to retrieve information from Frappe MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters data from Frappe/ERPNext documents but does not create, modify, delete, or execute any operations. The read-only nature of the server and the tool's design (accepting only filter and field parameters for query purposes) clearly places it in the Read category with low severity. An AI agent misuse would at worst retrieve sensitive data, but cannot modify or destroy records.
From the tool's definition Server is explicitly described as 'Read-only MCP server'; tool performs generic list/query operations with no mutation capability. Parameters are filters and field selection only, no write/delete/execute operations.
Attacks that exploit this kind of access
Generic Frappe list. doctype=DocType name; filters_json is a JSON list of [field, op, value] triples; fields_json is a JSON list of field names. Use this when the FranOS-specific tools don't fit (e.g. for ERPNext's Sales Invoice, GL Entry, Customer). It is categorised as a Read tool in the Frappe MCP MCP Server, which means it retrieves data without modifying state.
Register the Frappe MCP server in PolicyLayer and add a rule for frappe_list_docs: 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 Frappe MCP. Nothing to install.
frappe_list_docs 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 frappe_list_docs 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 frappe_list_docs. 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.
frappe_list_docs is provided by the Frappe MCP server (tourscale-repos/frappe-mcp). 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 →