read_source
Read a bounded UTF-8 source chunk. Omit versionId for the current baseline, or select a listed archive version as reference material. Only current source paths are readable. Use nextOffsetBytes for the next chunk; digest identifies the complete file in the selected version.
This record as markdown: /tools/0sec/read-source.md
What read_source does on 0sec
AI agents call read_source to retrieve information from 0sec without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why read_source is rated Low
Retrieves source code content without modification or execution capabilities.
From the tool's definition Read a bounded UTF-8 source chunk. Only current source paths are readable.
Attacks that exploit this kind of access
The rule that runs read_source safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0sec, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_source, this is the rule to start with:
read_source is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0sec, apply this rule, and every read_source call is checked against it from then on.
Questions about read_source
Read a bounded UTF-8 source chunk. Omit versionId for the current baseline, or select a listed archive version as reference material. Only current source paths are readable. Use nextOffsetBytes for the next chunk; digest identifies the complete file in the selected version. It is categorised as a Read tool in the 0sec MCP Server, which means it retrieves data without modifying state.
Register the 0sec MCP server in PolicyLayer and add a rule for read_source: 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 0sec. Nothing to install.
read_source 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_source 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_source. 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_source is provided by the 0sec MCP server (0sec-labs/0sec). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0sec, and thousands of servers like it.
This server
Across the catalogue