Parse a documentation page (HTML, markdown, or text) and extract shortcuts, workflows, and tips. Merges extracted knowledge into the app
AI agents use ingest_documentation to create or update resources in ScreenHand — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ScreenHand environment.
The tool reads a documentation page but its primary effect is writing/merging extracted knowledge into the app's internal state. This is a reversible data modification (Write), not merely a read operation. Severity is medium because an AI agent could inject malicious or incorrect shortcuts/workflows into the app's knowledge base by pointing it at adversarial content.
From the tool's definition 'Merges extracted knowledge into the app' — the tool parses external documentation and writes/merges the extracted data into the application's knowledge store
Documented attack patterns abuse exactly the kind of access ingest_documentation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for ingest_documentation:
{
"version": "1",
"default": "deny",
"tools": {
"ingest_documentation": {
"limits": [
{
"counter": "ingest_documentation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}ingest_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.
Parse a documentation page (HTML, markdown, or text) and extract shortcuts, workflows, and tips. Merges extracted knowledge into the app. It is categorised as a Write tool in the ScreenHand MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ScreenHand MCP server in PolicyLayer and add a rule for ingest_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 ScreenHand. Nothing to install.
ingest_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 ingest_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 ingest_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.
ingest_documentation is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.