AI agents use add_documentation to create or update resources in MCP-Ragdocs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Ragdocs environment.
This tool creates new records in the vector database by ingesting documentation from external URLs. While reversible (documentation can be removed), it modifies the system state and could be misused to inject malicious, misleading, or irrelevant documentation into the knowledge base that subsequent search queries would retrieve.
From the tool's definition Tool description states it "Add[s] documentation from a URL to the RAG database". The verb 'add' and action of persisting data to a database indicate a Write operation that modifies the documentation store.
Documented attack patterns abuse exactly the kind of access add_documentation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Ragdocs, and nothing reaches the server without passing your rules. This is the rule we recommend for add_documentation:
{
"version": "1",
"default": "deny",
"tools": {
"add_documentation": {
"limits": [
{
"counter": "add_documentation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_documentation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add documentation from a URL to the RAG database. It is categorised as a Write tool in the MCP-Ragdocs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-Ragdocs MCP server in PolicyLayer and add a rule for add_documentation: 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-Ragdocs. Nothing to install.
add_documentation 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_documentation 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_documentation. 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_documentation is provided by the MCP-Ragdocs MCP server (qpd-v/mcp-ragdocs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 MCP-Ragdocs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 MCP-Ragdocs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.