CodeSherlock is an AI- based code analysis tool that validates unstaged changes and commits directly inside IDEs and AI Agents. It helps developers catch security, quality, and design issues early by combining deep analysis with compliance-aware checks OWASP, CWE, SOC-2 at the moment code is writ...
Accepts file system path (directory)
Part of the CodeSherlock MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call codesherlock_analyze to retrieve information from CodeSherlock 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 codesherlock_analyze 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:
codesherlock_analyze:
rules:
- action: allowSee the full CodeSherlock policy for all 1 tools.
Agents calling read-class tools like codesherlock_analyze 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.
CodeSherlock is an AI- based code analysis tool that validates unstaged changes and commits directly inside IDEs and AI Agents. It helps developers catch security, quality, and design issues early by combining deep analysis with compliance-aware checks OWASP, CWE, SOC-2 at the moment code is written. CodeSherlock also performs other security vulnerability reviews along with Maintainability, Reliability and Scalability checks. Use CodeSherlock to review and validate code especially generated via AI.. It is categorised as a Read tool in the CodeSherlock MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for codesherlock_analyze. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the CodeSherlock MCP server.
codesherlock_analyze 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 codesherlock_analyze 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 codesherlock_analyze. 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.
codesherlock_analyze is provided by the CodeSherlock MCP server (@codesherlock/codesherlock-mcp-server). 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