Show, set, or clear typed metadata filters that automatically apply to retrieval and list commands.
AI agents use morphik-filters 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 can set or clear metadata filters that affect how data is retrieved. The 'show' aspect is Read, but 'set' and 'clear' modify persistent filter state that automatically applies to subsequent operations, making it a Write action. Misuse could cause an AI agent to silently retrieve unintended data by altering filter scope, giving it medium severity.
From the tool's definition Show, set, or clear typed metadata filters that automatically apply to retrieval and list commands
Documented attack patterns abuse exactly the kind of access morphik-filters 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 morphik-filters:
{
"version": "1",
"default": "deny",
"tools": {
"morphik-filters": {
"limits": [
{
"counter": "morphik-filters_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}morphik-filters 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.
Show, set, or clear typed metadata filters that automatically apply to retrieval and list commands. 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 morphik-filters: 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.
morphik-filters 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 morphik-filters 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 morphik-filters. 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.
morphik-filters 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.