AI agents use add_repository to create or update resources in MCP Code Analysis Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Code Analysis Server environment.
This tool creates a new entry in the server's repository tracking system. While reversible (the repository can be removed via delete_repository), it modifies state by adding a new repository to the managed set. The severity is medium because misuse could cause the server to track unintended repositories or consume resources, but the impact is limited to the analysis server's scope and the operation is reversible.
From the tool's definition Tool name 'add_repository' combined with description 'Add a new repository to track' indicates a CREATE/ADD operation that modifies the server's tracked repositories list.
Documented attack patterns abuse exactly the kind of access add_repository gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Code Analysis Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_repository:
{
"version": "1",
"default": "deny",
"tools": {
"add_repository": {
"limits": [
{
"counter": "add_repository_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_repository stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a new repository to track. It is categorised as a Write tool in the MCP Code Analysis Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Code Analysis Server MCP server in PolicyLayer and add a rule for add_repository: 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 MCP Code Analysis Server. Nothing to install.
add_repository is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_repository 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 add_repository. 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.
add_repository is provided by the MCP Code Analysis Server MCP server (johannhartmann/mcpcodeanalysis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Code Analysis 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.
44 MCP Code Analysis Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.