Detects duplicate and near-duplicate functions across the codebase using semantic code embeddings. USE WHEN: cleaning up code, finding copy-paste patterns, identifying refactoring opportunities, or auditing code quality. Returns pairs of similar functions ranked by similarity score. Works across ...
Risk signalsAccepts URL/endpoint input (uri)
Part of the Codegraph server.
Free to start. No card required.
AI agents call codegraph_find_duplicates to retrieve information from Codegraph 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 codegraph_find_duplicates 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": {
"codegraph_find_duplicates": {}
}
}See the full Codegraph policy for all 38 tools.
These attack patterns abuse exactly the kind of access codegraph_find_duplicates 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.
Detects duplicate and near-duplicate functions across the codebase using semantic code embeddings. USE WHEN: cleaning up code, finding copy-paste patterns, identifying refactoring opportunities, or auditing code quality. Returns pairs of similar functions ranked by similarity score. Works across languages — can find a Python function duplicated in Go. Threshold 0.7 catches renamed-variable clones, 0.9+ finds near-exact copies. Powered by Jina Code V2 embeddings trained on 150M+ code pairs.. It is categorised as a Read tool in the Codegraph MCP Server, which means it retrieves data without modifying state.
Register the Codegraph MCP server in PolicyLayer and add a rule for codegraph_find_duplicates: 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 Codegraph. Nothing to install.
codegraph_find_duplicates 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 codegraph_find_duplicates 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 codegraph_find_duplicates. 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.
codegraph_find_duplicates is provided by the Codegraph MCP server (codegraph-ai/CodeGraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 38 Codegraph 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.