AI agents invoke pandoc_convert to trigger actions in SiYuan MCP Server. 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.
Pandoc is an external program/binary that gets executed to convert documents between formats. Running external processes constitutes Execute-level risk, as the arguments determine what is run and output. The description is minimal ('Pandoc conversion'), lowering confidence slightly, but the tool name clearly implies invoking the Pandoc executable.
From the tool's definition Tool name 'pandoc_convert' and description 'Pandoc 转换' (Pandoc conversion) indicate running the Pandoc document conversion tool
Documented attack patterns abuse exactly the kind of access pandoc_convert gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SiYuan MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for pandoc_convert:
{
"version": "1",
"default": "deny",
"tools": {
"pandoc_convert": {
"limits": [
{
"counter": "pandoc_convert_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}pandoc_convert 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.
Free to start. No card required.
Pandoc 转换. It is categorised as a Execute tool in the SiYuan MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SiYuan MCP Server MCP server in PolicyLayer and add a rule for pandoc_convert: 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 SiYuan MCP Server. Nothing to install.
pandoc_convert 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 pandoc_convert 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 pandoc_convert. 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.
pandoc_convert is provided by the SiYuan MCP Server MCP server (xgq18237/siyuan_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 52 SiYuan MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
52 SiYuan MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.