Low Risk

pubchem_get_compound_xrefs

Get external database cross-references for a compound: PubMed citations, patent IDs, gene/protein associations, registry numbers, and taxonomy IDs. Results are capped per type with total counts reported.

Part of the Pubchem server.

pubchem_get_compound_xrefs is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE PUBCHEM →

Free to start. No card required.

AI agents call pubchem_get_compound_xrefs to retrieve information from Pubchem without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though pubchem_get_compound_xrefs only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

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

See the full Pubchem policy for all 10 tools.

Get this rule live on your own Pubchem server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY PUBCHEM →

View all 10 tools →

These attack patterns abuse exactly the kind of access pubchem_get_compound_xrefs gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so pubchem_get_compound_xrefs only ever does what you allow.

SECURE PUBCHEM →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the pubchem_get_compound_xrefs tool do? +

Get external database cross-references for a compound: PubMed citations, patent IDs, gene/protein associations, registry numbers, and taxonomy IDs. Results are capped per type with total counts reported.. It is categorised as a Read tool in the Pubchem MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on pubchem_get_compound_xrefs? +

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

What risk level is pubchem_get_compound_xrefs? +

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

Can I rate-limit pubchem_get_compound_xrefs? +

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

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

pubchem_get_compound_xrefs is provided by the Pubchem MCP server (https://pubchem.caseyjhand.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pubchem tool call.

Deterministic rules across all 10 Pubchem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.