Low Risk

search_by_name

Resolve a common chemical or drug name to PubChem CIDs. Use for "what's the CID of ibuprofen?" or to disambiguate. Returns CIDs (Compound IDs) matched to the name. Then use get_compound with the CID for properties.

Part of the Pubchem server.

search_by_name 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 search_by_name 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 search_by_name 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": {
    "search_by_name": {}
  }
}

See the full Pubchem policy for all 24 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 24 tools →

These attack patterns abuse exactly the kind of access search_by_name 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 search_by_name 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 search_by_name tool do? +

Resolve a common chemical or drug name to PubChem CIDs. Use for "what's the CID of ibuprofen?" or to disambiguate. Returns CIDs (Compound IDs) matched to the name. Then use get_compound with the CID for properties.. 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 search_by_name? +

Register the Pubchem MCP server in PolicyLayer and add a rule for search_by_name: 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 search_by_name? +

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

Can I rate-limit search_by_name? +

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

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

search_by_name is provided by the Pubchem MCP server (https://gateway.pipeworx.io/pubchem/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 24 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.