Get completion suggestions for a position in a document using Language Server Protocol
AI agents call get_completions to retrieve information from MCP Package Docs Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries a Language Server Protocol implementation to fetch code completion suggestions at a specific document position. This is a read-only information retrieval operation with no side effects, no code execution, no data modification, and no destructive capability.
From the tool's definition Tool description states 'Get completion suggestions for a position in a document using Language Server Protocol' — this retrieves suggestions based on document context without modifying data or executing external operations.
Documented attack patterns abuse exactly the kind of access get_completions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Package Docs Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_completions:
{
"version": "1",
"default": "deny",
"tools": {
"get_completions": {}
}
}get_completions 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.
Get completion suggestions for a position in a document using Language Server Protocol. It is categorised as a Read tool in the MCP Package Docs Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Package Docs Server MCP server in PolicyLayer and add a rule for get_completions: 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 Package Docs Server. Nothing to install.
get_completions 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 get_completions 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 get_completions. 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.
get_completions is provided by the MCP Package Docs Server MCP server (sammcj/mcp-package-docs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 MCP Package Docs Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 MCP Package Docs Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.