Add raw text into Morphik so it becomes searchable and available for retrieval.
AI agents use ingest-text to create or update resources in Morphik MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Morphik MCP environment.
This tool creates new data entries in the Morphik multi-modal database system. While it is reversible (documents can be deleted via the sibling delete-document tool), it permanently alters the database state and modifies searchable content.
From the tool's definition Tool description explicitly states 'Add raw text into Morphik' — a creation/modification operation that persists data.
Documented attack patterns abuse exactly the kind of access ingest-text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Morphik MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ingest-text:
{
"version": "1",
"default": "deny",
"tools": {
"ingest-text": {
"limits": [
{
"counter": "ingest-text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}ingest-text 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 raw text into Morphik so it becomes searchable and available for retrieval. It is categorised as a Write tool in the Morphik MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Morphik MCP server in PolicyLayer and add a rule for ingest-text: 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 Morphik MCP. Nothing to install.
ingest-text 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-text 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-text. 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-text is provided by the Morphik MCP server (morphik-org/morphik-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Morphik MCP, 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.
17 Morphik MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.