Low Risk

read_full_buf

read_full_buf

How to control read_full_buf ↓

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

Low Risk

Despite the empty description, the naming convention strongly suggests this tool retrieves/queries the full contents of a Neovim buffer without modification. The tool is part of a Neovim control interface where read operations (get_state, get_buf_diagnostics, get_all_diagnostics) coexist with write/modify operations (add_virtual_text, find_and_replace_buf), and this tool clearly belongs to the read category based on…

From the tool's definition Tool name 'read_full_buf' indicates reading buffer contents from a Neovim session. No side effects implied in the name or the description (which is empty). Sibling tools include get_state and get_state_brief, reinforcing a read-only context pattern.

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

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

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

read_full_buf 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 Nvim — 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.

Go deeper

What does the read_full_buf tool do? +

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

How do I enforce a policy on read_full_buf? +

Register the Nvim MCP server in PolicyLayer and add a rule for read_full_buf: 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 Nvim. Nothing to install.

What risk level is read_full_buf? +

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

Can I rate-limit read_full_buf? +

Yes. Add a rate_limit block to the read_full_buf 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 read_full_buf completely? +

Set action: deny in the PolicyLayer policy for read_full_buf. 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 read_full_buf? +

read_full_buf is provided by the Nvim MCP server (paulburgess1357/nvim-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nvim tool call.

Deterministic rules across all 17 Nvim tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

17 Nvim tools catalogued and risk-classified — across an index of 42,500+ 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.