AI agents call git_blame to retrieve information from Coding Tools MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
git_blame retrieves historical authorship and commit information about code lines. This is purely a read operation with no side effects. It does not execute code, modify files, delete data, or perform financial transactions. Given the context of a coding tools server alongside other version control commands (git_diff, git_log, git_show, git_status), this classification is straightforward.
From the tool's definition Tool name is 'git_blame' which is a standard Git command that displays the commit history and authorship of lines in a file.
Documented attack patterns abuse exactly the kind of access git_blame gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Coding Tools MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for git_blame:
{
"version": "1",
"default": "deny",
"tools": {
"git_blame": {}
}
}git_blame is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
git_blame. It is categorised as a Read tool in the Coding Tools MCP MCP Server, which means it retrieves data without modifying state.
Register the Coding Tools MCP server in PolicyLayer and add a rule for git_blame: 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 Coding Tools MCP. Nothing to install.
git_blame 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 git_blame 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 git_blame. 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.
git_blame is provided by the Coding Tools MCP server (xytom/coding-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Coding Tools MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Coding Tools MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.