state_proposition
State a proposition — a claim about the world we act on — as PROPOSED: the statement as one sentence, the rationale, the FALSIFIER (the observation that would show it false; required, because a proposition with no falsifier is a slogan), the initial confidence 0-1 (recorded as the first reading, ...
This record as markdown: /tools/adrata-adrata-mcp/state-proposition.md
What state_proposition does on Adrata
AI agents use state_proposition to create or update resources in Adrata, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adrata environment.
Why state_proposition is rated Medium
An AI agent can call state_proposition faster than any human can review: one bad instruction and it creates or modifies resources in Adrata by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs state_proposition safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For state_proposition, this is the rule to start with:
state_proposition 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every state_proposition call is checked against it from then on.
Questions about state_proposition
State a proposition — a claim about the world we act on — as PROPOSED: the statement as one sentence, the rationale, the FALSIFIER (the observation that would show it false; required, because a proposition with no falsifier is a slogan), the initial confidence 0-1 (recorded as the first reading, so calibration can score it later), audience and a review date. To replace a claim, state a NEW one with supersedesPropositionId — the old one moves to superseded and keeps its readings; never edit the old statement. Link what rests on it with link_proposition afterwards.${GOVERNED_NOTE}. It is categorised as a Write tool in the Adrata MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Adrata MCP server in PolicyLayer and add a rule for state_proposition: 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 Adrata. Nothing to install.
state_proposition 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 state_proposition 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 state_proposition. 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.
state_proposition is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
This server
Across the catalogue