Low Risk

search_defects

search_defects

How to control search_defects ↓

What search_defects does on Coverity Connect MCP Server

AI agents call search_defects to retrieve information from Coverity Connect MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_defects needs a policy

The tool searches for defects in a static analysis platform, which retrieves security vulnerability data without modifying it. While defect information could be sensitive and potentially leak information about security weaknesses in systems, the operation itself is read-only.

From the tool's definition Tool name 'search_defects' indicates query/search functionality typical of Read operations. Sibling tools like 'get_defect_details', 'get_project_summary', and 'list_projects' establish a pattern of read-only retrieval from the Coverity Connect platform.

Documented attack patterns abuse exactly the kind of access search_defects gives an agent:

How to control search_defects

PolicyLayer is an MCP gateway — it sits between your AI agents and Coverity Connect MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_defects:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_defects": {}
  }
}

search_defects is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Coverity Connect MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_defects

What does the search_defects tool do? +

search_defects. It is categorised as a Read tool in the Coverity Connect MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_defects? +

Register the Coverity Connect MCP Server MCP server in PolicyLayer and add a rule for search_defects: 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 Coverity Connect MCP Server. Nothing to install.

What risk level is search_defects? +

search_defects is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_defects? +

Yes. Add a rate_limit block to the search_defects 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.

How do I block search_defects completely? +

Set action: deny in the PolicyLayer policy for search_defects. 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.

What MCP server provides search_defects? +

search_defects is provided by the Coverity Connect MCP Server MCP server (keides2/coverity-connect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Coverity Connect MCP Server tool call.

Start from Coverity Connect MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

8 Coverity Connect MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.