copilot_complete
Generate a code completion via the dev's local Ollama model. Supports fill-in-the-middle via prefix+suffix for Qwen2.5-Coder / StarCoder / DeepSeek. Replaces GitHub Copilot / Cursor for solo devs running Ollama.
This record as markdown: /tools/io-github-kivanccakmak-yaver/copilot-complete.md
What copilot_complete does on Yaver
AI agents invoke copilot_complete to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
file | string | — | |
model | string | — | Ollama tag, default qwen2.5-coder:7b |
prefix | string | Yes | Text before the cursor |
suffix | string | — | Text after the cursor for FIM |
language | string | — | |
maxTokens | integer | — | |
temperature | number | — |
Parameters from the server's own tool schema.
Why copilot_complete is rated High
This tool triggers execution of a local AI model (Ollama) to generate code completions. It doesn't merely read static data — it actively invokes an external inference process. While it doesn't run generated code itself, it executes an external model operation whose output depends on the input arguments.
From the tool's definition "Generate a code completion via the dev's local Ollama model" and "Replaces GitHub Copilot / Cursor for solo devs running Ollama"
Risk signalsAccepts file system path (file)
Attacks that exploit this kind of access
The rule that runs copilot_complete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For copilot_complete, this is the rule to start with:
copilot_complete stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every copilot_complete call is checked against it from then on.
Questions about copilot_complete
Generate a code completion via the dev's local Ollama model. Supports fill-in-the-middle via prefix+suffix for Qwen2.5-Coder / StarCoder / DeepSeek. Replaces GitHub Copilot / Cursor for solo devs running Ollama. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
copilot_complete accepts 7 parameters: file, model, prefix, suffix, language, maxTokens, temperature. Required: prefix. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for copilot_complete: 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 Yaver. Nothing to install.
copilot_complete is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the copilot_complete 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 copilot_complete. 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.
copilot_complete is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
Across the catalogue