AI agents call read_file_by_path to retrieve information from Kontexta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents from disk without side effects. It is a simple read operation analogous to 'get' or 'fetch'. No data is modified, deleted, executed, or at financial risk. The local-first architecture and controlled context budgeting further suggest safe, passive access.
From the tool's definition Tool name 'read_file_by_path' and description indicate file lookup/retrieval ('Look up a file by its absolute on-disk path and return the same shape as') with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Look up a file by its absolute on-disk path and return the same shape as. It is categorised as a Read tool in the Kontexta MCP Server, which means it retrieves data without modifying state.
Register the Kontexta MCP server in PolicyLayer and add a rule for read_file_by_path: 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 Kontexta. Nothing to install.
read_file_by_path 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_file_by_path 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_file_by_path. 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_file_by_path is provided by the Kontexta MCP server (safiyu/kontexta). 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 →