[DEPRECATED] Returns only basic spec metadata with empty dependencies/dependents arrays (upstream web-specs does not expose dependency data). Scheduled for removal in the next major release — use get_w3c_spec instead.
AI agents call get_spec_dependencies to retrieve information from W3c without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries web specification data without side effects. Despite being deprecated, it performs only data retrieval (querying spec metadata), making it a Read operation. The low severity reflects the informational nature of the data—web standards documentation poses minimal risk even if an AI agent misuses access to it. The tool cannot modify, delete, or execute anything.
From the tool's definition Tool returns specification metadata with dependencies and dependents arrays; described as retrieving 'basic spec metadata' with no modification, deletion, or execution capabilities. The 'get' prefix and return-only behavior indicate a read operation.
Attacks that exploit this kind of access
[DEPRECATED] Returns only basic spec metadata with empty dependencies/dependents arrays (upstream web-specs does not expose dependency data). Scheduled for removal in the next major release — use get_w3c_spec instead. It is categorised as a Read tool in the W3c MCP Server, which means it retrieves data without modifying state.
Register the W3c MCP server in PolicyLayer and add a rule for get_spec_dependencies: 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 W3c. Nothing to install.
get_spec_dependencies 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 get_spec_dependencies 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 get_spec_dependencies. 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.
get_spec_dependencies is provided by the W3c MCP server (shuji-bonji/w3c-mcp). 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 →