Mechanism of action records (filtered by molecule_chembl_id).
AI agents call mechanism to retrieve information from Mcp Chembl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a filtered query to retrieve mechanism of action information associated with molecular ChEMBL IDs. It is purely informational/read-only with no side effects, no code execution, no data modification, and no destructive operations. The low severity reflects the benign nature of querying a public drug discovery database.
From the tool's definition Tool description states 'Mechanism of action records (filtered by molecule_chembl_id)' - this is a retrieval operation that queries and returns data from the ChEMBL database without modifying, deleting, or executing any operations.
Attacks that exploit this kind of access
Mechanism of action records (filtered by molecule_chembl_id). It is categorised as a Read tool in the Mcp Chembl MCP Server, which means it retrieves data without modifying state.
Register the Mcp Chembl MCP server in PolicyLayer and add a rule for mechanism: 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 Mcp Chembl. Nothing to install.
mechanism is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mechanism 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 mechanism. 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.
mechanism is provided by the Mcp Chembl MCP server (pipeworx-io/mcp-chembl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →