Ingest a C++ codebase and build its dependency graph. This tool does NOT accept 'code_content'. Provide exactly ONE of: repo_url, raw_files, or directory_path. - repo_url: an HTTPS GitHub URL (e.g. 'https://github.com/user/repo'). Optionally add patch_content (a unified diff string) to overlay un...
Part of the GraphPulse C++ server.
Free to start. No card required.
AI agents call analyze_codebase to retrieve information from GraphPulse C++ 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 analyze_codebase 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.
{
"version": "1",
"default": "deny",
"tools": {
"analyze_codebase": {}
}
}See the full GraphPulse C++ policy for all 8 tools.
These attack patterns abuse exactly the kind of access analyze_codebase gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Ingest a C++ codebase and build its dependency graph. This tool does NOT accept 'code_content'. Provide exactly ONE of: repo_url, raw_files, or directory_path. - repo_url: an HTTPS GitHub URL (e.g. 'https://github.com/user/repo'). Optionally add patch_content (a unified diff string) to overlay uncommitted changes on the cloned repo. - raw_files: for hobby projects or small codebases NOT hosted on GitHub. The user pastes their C++ code directly and you wrap each file into a JSON array of objects with 'filename' and 'content' keys. Example: [ {"filename": "main.cpp", "content": "void main() { helper(); }"}, {"filename": "utils.cpp", "content": "void helper() {}"} ] - directory_path: absolute local filesystem path (local mode only; rejected when the server runs in cloud mode). Args: repo_url: HTTPS URL of a git repository to clone. patch_content: Unified diff to apply after cloning repo_url. raw_files: List of dicts [{"filename": str, "content": str}]. Use this when the user shares code snippets directly and does not have a git repository. directory_path: Local path to scan (local mode only). Returns: Status message with file count and function count.. It is categorised as a Read tool in the GraphPulse C++ MCP Server, which means it retrieves data without modifying state.
Register the GraphPulse C++ MCP server in PolicyLayer and add a rule for analyze_codebase: 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 GraphPulse C++. Nothing to install.
analyze_codebase 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 analyze_codebase 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 analyze_codebase. 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.
analyze_codebase is provided by the GraphPulse C++ MCP server (labsofuniverse/legacy-mcp-analyzer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 GraphPulse C++ tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.