Scan project source code for content strings. Three modes: "graph" builds import/component graph for project intelligence, "candidates" extracts string literals with pre-filtering and pagination, "summary" provides quick overview stats. Read-only — no changes to disk or git. MCP finds strings det...
Part of the Contentrain MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call contentrain_scan to retrieve information from Contentrain without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though contentrain_scan only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
contentrain_scan:
rules:
- action: allowSee the full Contentrain policy for all 15 tools.
Agents calling read-class tools like contentrain_scan have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Scan project source code for content strings. Three modes: "graph" builds import/component graph for project intelligence, "candidates" extracts string literals with pre-filtering and pagination, "summary" provides quick overview stats. Read-only — no changes to disk or git. MCP finds strings deterministically; the agent decides what is content. Recommended workflow: start with "summary" or "graph" for orientation, then paginate through "candidates" to evaluate strings.. It is categorised as a Read tool in the Contentrain MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for contentrain_scan. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Contentrain MCP server.
contentrain_scan 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 contentrain_scan rule in your Intercept 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 Intercept policy for contentrain_scan. 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.
contentrain_scan is provided by the Contentrain MCP server (@contentrain/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept