Crawls a documentation site (sitemap.xml first, BFS fallback) and indexes every page into the local DB. Idempotent: a second call for the same base URL returns the existing site (and folds into any in-flight crawl). Pass wait:false to run the crawl in the background.
AI agents use add_site to create or update resources in Docs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docs environment.
This tool creates new records in a SQLite database by crawling and indexing documentation sites. While the operation is reversible (sites can be removed via remove_site and re-indexed), it modifies persistent state in the local database. This fits the Write category: it creates or modifies data reversibly.
From the tool's definition The tool description states it 'indexes every page into the local DB' and 'a second call for the same base URL returns the existing site', indicating it creates and modifies database records.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Crawls a documentation site (sitemap.xml first, BFS fallback) and indexes every page into the local DB. Idempotent: a second call for the same base URL returns the existing site (and folds into any in-flight crawl). Pass wait:false to run the crawl in the background. It is categorised as a Write tool in the Docs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docs MCP server in PolicyLayer and add a rule for add_site: 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 Docs. Nothing to install.
add_site 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_site 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_site. 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_site is provided by the Docs MCP server (kage1020/docs-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 →