AI agents use add_to_library to create or update resources in NASA ADS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NASA ADS MCP Server environment.
This tool modifies user library data by adding paper references, but the changes are reversible (papers can be removed). There are no financial implications, no code execution, no data deletion, and no destructive effects. It clearly falls under Write category as it creates or modifies data in a non-destructive manner.
From the tool's definition Tool name 'add_to_library' and description 'Add papers to an existing library' indicate creation/modification of library contents. This is a write operation that creates new associations between papers and libraries.
Documented attack patterns abuse exactly the kind of access add_to_library gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NASA ADS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_to_library:
{
"version": "1",
"default": "deny",
"tools": {
"add_to_library": {
"limits": [
{
"counter": "add_to_library_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_to_library stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add papers to an existing library. It is categorised as a Write tool in the NASA ADS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NASA ADS MCP Server MCP server in PolicyLayer and add a rule for add_to_library: 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 NASA ADS MCP Server. Nothing to install.
add_to_library is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_to_library 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 add_to_library. 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.
add_to_library is provided by the NASA ADS MCP Server MCP server (prtc/nasa-ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NASA ADS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 NASA ADS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.